• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Suzuki Taiji  鈴木 大慈

ORCIDConnect your ORCID iD *help
… Alternative Names

SUZUKI Taiji  鈴木 大慈

Less
Researcher Number 60551372
Other IDs
Affiliation (Current) 2025: 東京大学, 大学院情報理工学系研究科, 教授
2025: 国立研究開発法人理化学研究所, 革新知能統合研究センター, チームディレクター
Affiliation (based on the past Project Information) *help 2024: 東京大学, 大学院情報理工学系研究科, 教授
2017 – 2024: 東京大学, 大学院情報理工学系研究科, 准教授
2019: 東京工業大学, 情報理工学研究科, 准教授
2016: 東京大学, 情報理工学系研究科, 准教授
2016: 東京工業大学, その他部局等, 准教授 … More
2016: 東京工業大学, 情報理工学院, 准教授
2015: 東京工業大学, 大学院情報理工学研究科, 准教授
2015: 東京工業大学, 情報理工学研究科, 准教授
2013 – 2015: 東京工業大学, 情報理工学(系)研究科, 准教授
2012: 東京大学, 大学院・情報理工学系研究科, 助教
2011 – 2012: 東京大学, 情報理工学(系)研究科, 助教
2010: 東京大学, 大学院・情報理工学系研究科, 助教 Less
Review Section/Research Field
Principal Investigator
Sections That Are Subject to Joint Review: Basic Section60030:Statistical science-related , Basic Section61030:Intelligent informatics-related / Basic Section 61030:Intelligent informatics-related / Basic Section 60030:Statistical science-related / Basic Section 60010:Theory of informatics-related / Statistical science / Statistical science
Except Principal Investigator
Medium-sized Section 60:Information science, computer engineering, and related fields / Statistical science / Mathematical informatics / Complex systems
Keywords
Principal Investigator
機械学習 / 統計的学習理論 / 深層学習 / 高次元統計 / 確率的最適化 / 基盤モデル / 最適化 / 構造解析 / 学習理論 / 数理統計 … More / 汎化誤差 / モデル圧縮 / ノンパラメトリック統計 / 汎化誤差解析 / カーネル法 / 低ランク行列 / 交互方向定数法 / ベイズ統計 / ガウシアンプロセス事前分布 / 交互方向乗数法 / 交互最適化 / 低ランクテンソル推定 / ビッグデータ / 確率密度比 / スパース推定 / 統計的学習 / ガウシアンプロセス / 再生核ヒルベルト空間 / ベイズ推定 / テンソルモデリング / 構造的正則化 / 統計数学 / 正則化 / スパース学習 / 近接勾配法 / 双対平均化法 / オンライン最適化 / スパース加法モデル / multiple kernel learning … More
Except Principal Investigator
高次元データ / 深層学習 / 機械学習 / 統計数学 / アルゴリズム / 高次元小標本 / 高次元統計解析 / 時空間データ / マイクロアレイ / ゲノム / データサイエンス / 理論解析 / ニューラルネットワーク / 人工知能 / 数理的基盤 / 動的ネットワークバイオマーカー / 内分泌療法 / 個別化医療 / 数理モデリング / 生命病態システム / 統計的学習理論 / 高次元 / データ解析 / 最適化 / ベイズ推論 / セミパラメトリック / スパースモデリング Less
  • Research Projects

    (10 results)
  • Research Products

    (412 results)
  • Co-Researchers

    (39 People)
  •  大規模基盤モデルの革新的原理解明と方法論の新展開Principal Investigator

    • Principal Investigator
      鈴木 大慈
    • Project Period (FY)
      2024 – 2028
    • Research Category
      Grant-in-Aid for Scientific Research (B)
    • Review Section
      Basic Section 60030:Statistical science-related
      Basic Section 61030:Intelligent informatics-related
      Sections That Are Subject to Joint Review: Basic Section60030:Statistical science-related , Basic Section61030:Intelligent informatics-related
    • Research Institution
      The University of Tokyo
  •  Innovative Developments of Theories and Methodologies for Large Complex Data

    • Principal Investigator
      青嶋 誠
    • Project Period (FY)
      2020 – 2024
    • Research Category
      Grant-in-Aid for Scientific Research (A)
    • Review Section
      Medium-sized Section 60:Information science, computer engineering, and related fields
    • Research Institution
      University of Tsukuba
  •  Advance of artificial intelligence by theoretical investigation of deep learning

    • Principal Investigator
      Fukumizu Kenji
    • Project Period (FY)
      2018 – 2020
    • Research Category
      Grant-in-Aid for Challenging Research (Exploratory)
    • Review Section
      Medium-sized Section 60:Information science, computer engineering, and related fields
    • Research Institution
      The Institute of Statistical Mathematics
  •  Intensifying deep learning theory and its application to structure analysis of deep neural networkPrincipal Investigator

    • Principal Investigator
      Suzuki Taiji
    • Project Period (FY)
      2018 – 2021
    • Research Category
      Grant-in-Aid for Scientific Research (B)
    • Review Section
      Basic Section 60010:Theory of informatics-related
    • Research Institution
      The University of Tokyo
  •  Establishing Theoretical Foundations for Mathematical Modeling of Pathological Biosystems and its Applications to Personalized Medicine

    • Principal Investigator
      AIHARA Kazuyuki
    • Project Period (FY)
      2015 – 2019
    • Research Category
      Grant-in-Aid for Scientific Research (S)
    • Research Field
      Mathematical informatics
    • Research Institution
      The University of Tokyo
  •  Theories and Methodologies for Large Complex Data

    • Principal Investigator
      AOSHIMA Makoto
    • Project Period (FY)
      2015 – 2019
    • Research Category
      Grant-in-Aid for Scientific Research (A)
    • Research Field
      Statistical science
    • Research Institution
      University of Tsukuba
  •  Thery and methods for high dimensional data analysis with internal structure

    • Principal Investigator
      Fukumizu Kenji
    • Project Period (FY)
      2014 – 2018
    • Research Category
      Grant-in-Aid for Scientific Research (B)
    • Research Field
      Statistical science
    • Research Institution
      The Institute of Statistical Mathematics
  •  Deepening and applications of sparse modeling by approaches of semiparametric Bayesian inference

    • Principal Investigator
      Fukumizu Kenji
    • Project Period (FY)
      2013 – 2017
    • Research Category
      Grant-in-Aid for Scientific Research on Innovative Areas (Research in a proposed research area)
    • Review Section
      Complex systems
    • Research Institution
      The Institute of Statistical Mathematics
  •  Theories of structured estimation methods for large scale data and their applicationsPrincipal Investigator

    • Principal Investigator
      SUZUKI Taiji
    • Project Period (FY)
      2013 – 2017
    • Research Category
      Grant-in-Aid for Young Scientists (B)
    • Research Field
      Statistical science
    • Research Institution
      The University of Tokyo
      Tokyo Institute of Technology
  •  Theory and applications of cross-data-type machine learning methodsPrincipal Investigator

    • Principal Investigator
      SUZUKI Taiji
    • Project Period (FY)
      2010 – 2012
    • Research Category
      Grant-in-Aid for Young Scientists (B)
    • Research Field
      Statistical science
    • Research Institution
      The University of Tokyo

All 2024 2023 2022 2021 2020 2019 2018 2017 2016 2015 2014 2013 2012 2011 2010 Other

All Journal Article Presentation Book Patent

  • [Book] 機械学習のための連続最適化2016

    • Author(s)
      金森敬文,鈴木大慈,竹内一郎,佐藤一誠
    • Total Pages
      352
    • Publisher
      講談社
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Book] 機械学習のための連続最適化2016

    • Author(s)
      金森敬文, 鈴木大慈, 竹内一郎, 佐藤一誠
    • Total Pages
      352
    • Publisher
      講談社
    • Data Source
      KAKENHI-PROJECT-15H01678
  • [Book] 確率的最適化(機械学習プロフェッショナルシリーズ)2015

    • Author(s)
      鈴木大慈
    • Total Pages
      176
    • Publisher
      講談社
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Book] 確率的最適化(機械学習プロフェッショナルシリーズ)2015

    • Author(s)
      鈴木大慈
    • Total Pages
      176
    • Publisher
      講談社
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Book] 確率的最適化2015

    • Author(s)
      鈴木大慈
    • Total Pages
      176
    • Publisher
      講談社
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Book] 確率的最適化(機械学習プロフェッショナルシリーズ)2015

    • Author(s)
      鈴木大慈
    • Total Pages
      176
    • Publisher
      講談社
    • Data Source
      KAKENHI-PROJECT-15H01678
  • [Book] 共立出版2014

    • Author(s)
      Trevor Hastie, Robert Tibshirani, Jerome Friedman (原著), 杉山 将, 井手 剛, 神嶌 敏弘, 栗田 多喜夫, 前田 英作(編), 鈴木大慈ほか(訳)
    • Total Pages
      888
    • Publisher
      統計的学習の基礎:データマイニング・推論・予測
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Book] 株式会社エヌ・ティー・エス2014

    • Author(s)
      嶋田茂,伊藤大雄,坂本 比呂志,當仲寛哲,鷲尾隆,上田修功,杉山将,鹿島久嗣,鈴木大慈,河原大輔,黒橋禎夫,関根聡,西尾信彦,稲越宏弥,ほか計36名
    • Total Pages
      240
    • Publisher
      ビッグデータ・マネジメント―データサイエンティストのためのデータ利活用技術と事例
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Book] ビッグデータ・マネジメント-データサイエンティストのためのデータ利活用技術と事例2013

    • Author(s)
      嶋田茂,伊藤大雄,坂本 比呂志,當仲寛哲,鷲尾隆,上田修功,杉山将,鹿島久嗣,鈴木大慈,河原大輔,黒橋禎夫,関根聡,西尾信彦,稲越宏弥,ほか計36名
    • Total Pages
      329
    • Publisher
      株式会社エヌ・ティー・エス
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Book] Density Ratio Estimation in Machine Learning2012

    • Author(s)
      Masashi Sugiyama, Taiji Suzuki, and Takafumi Kanamori
    • Total Pages
      329
    • Publisher
      Cambridge University Press
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Book] Cambridge UniversityPress2012

    • Author(s)
      Masashi Sugiyama, T aiji Suzuki, andTakafumi Kanamori
    • Total Pages
      329
    • Publisher
      Density Ratio Estimationin Machine Learning
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Journal Article] Anisotropy helps: improved statistical and computational complexity of the mean-field Langevin dynamics under structured data2024

    • Author(s)
      Atsushi Nitanda, Kazusato Oko, Taiji Suzuki, Denny Wu
    • Journal Title

      The Twelfth International Conference on Learning Representations

      Volume: ー

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Journal Article] Uniform-in-time propagation of chaos for the mean field gradient Langevin dynamics2023

    • Author(s)
      Taiji Suzuki, Atsushi Nitanda, Denny Wu
    • Journal Title

      The 11th International Conference on Learning Representations

      Volume: ー

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Journal Article] Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input2023

    • Author(s)
      Shokichi Takakura, Taiji Suzuki
    • Journal Title

      Proceedings of the 40th International Conference on Machine Learning

      Volume: 202 Pages: 33416-33447

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Journal Article] Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction2023

    • Author(s)
      Taiji Suzuki, Denny Wu, Atsushi Nitanda
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 37

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Journal Article] Diffusion Models are Minimax Optimal Distribution Estimators2023

    • Author(s)
      Kazusato Oko, Shunta Akiyama, Taiji Suzuki
    • Journal Title

      Proceedings of the 40th International Conference on Machine Learning

      Volume: 202 Pages: 26517-26582

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Journal Article] Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond2023

    • Author(s)
      Taiji Suzuki, Denny Wu, Kazusato Oko, Atsushi Nitanda
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 37

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Journal Article] Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning2022

    • Author(s)
      Tomoya Murata, Taiji Suzuki
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 35 Pages: 5039-5051

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Journal Article] High-dimensional asymptotics of feature learning: How one gradient step improves the representation2022

    • Author(s)
      Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Zhichao Wang, Denny Wu, Greg Yang
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 35 Pages: 32612-32623

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Journal Article] Understanding the Variance Collapse of SVGD in High Dimensions2022

    • Author(s)
      Jimmy Ba, Murat A Erdogdu, Marzyeh Ghassemi, Shengyang Sun, Taiji Suzuki, Denny Wu, and Tianzong Zhang
    • Journal Title

      ICLR2022

      Volume: 10

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Learnability of convolutional neural networks for infinite dimensional input via mixed and anisotropic smoothness2022

    • Author(s)
      Sho Okumoto and Taiji Suzuki
    • Journal Title

      ICLR2022

      Volume: 10

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Convex Analysis of the Mean Field Langevin Dynamics2022

    • Author(s)
      Atsushi Nitanda, Denny Wu, Taiji Suzuki
    • Journal Title

      AISTATS2022, Proceedings of Machine Learning Research

      Volume: 151

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective?2022

    • Author(s)
      Mikami Hiroaki、Fukumizu Kenji、Murai Shogo、Suzuki Shuji、Kikuchi Yuta、Suzuki Taiji、Maeda Shin-ichi、Hayashi Kohei
    • Journal Title

      Proceedings of Machine Learning and Knowledge Discovery in Databases, Part III. Springer Lecture Notes in Computer Science

      Volume: 13715 Pages: 477-492

    • DOI

      10.1007/978-3-031-26409-2_29

    • ISBN
      9783031264085, 9783031264092
    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Journal Article] Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization2022

    • Author(s)
      Kazusato Oko, Taiji Suzuki, Atsushi Nitanda, and Denny Wu
    • Journal Title

      ICLR2022

      Volume: 10

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Deep two-way matrix reordering for relational data analysis2022

    • Author(s)
      Watanabe Chihiro、Suzuki Taiji
    • Journal Title

      Neural Networks

      Volume: 146 Pages: 303-315

    • DOI

      10.1016/j.neunet.2021.11.028

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Journal Article] AutoLL: Automatic Linear Layout of Graphs based on Deep Neural Network2022

    • Author(s)
      Watanabe Chihiro、Suzuki Taiji
    • Journal Title

      IEEE Symposium Series on Computational Intelligence (SSCI 2021)

      Volume: - Pages: 1-10

    • DOI

      10.1109/ssci50451.2021.9659893

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime2021

    • Author(s)
      Atsushi Nitanda, and Taiji Suzuki
    • Journal Title

      ICLR2021

      Volume: 9

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error2021

    • Author(s)
      Suzuki Taiji、Abe Hiroshi、Murata Tomoya、Horiuchi Shingo、Ito Kotaro、Wachi Tokuma、Hirai So、Yukishima Masatoshi、Nishimura Tomoaki
    • Journal Title

      Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence

      Volume: Main track Pages: 2839-2846

    • DOI

      10.24963/ijcai.2020/393

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-15H05707, KAKENHI-PROJECT-18H03201
  • [Journal Article] Gradient Descent in RKHS with Importance Labeling2021

    • Author(s)
      Tomoya Murata, and Taiji Suzuki
    • Journal Title

      AISTATS2021, Proceedings of Machine Learning Research

      Volume: 130

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting2021

    • Author(s)
      Shunta Akiyama, Taiji Suzuki
    • Journal Title

      ICML2021, Proceedings of Machine Learning Research

      Volume: 139

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Estimation error analysis of deep learning on the regression problem on the variable exponent Besov space2021

    • Author(s)
      Tsuji Kazuma、Suzuki Taiji
    • Journal Title

      Electronic Journal of Statistics

      Volume: 15 Issue: 1 Pages: 1869-1908

    • DOI

      10.1214/21-ejs1828

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-20H00576, KAKENHI-PROJECT-18H03201
  • [Journal Article] When Does Preconditioning Help or Hurt Generalization?2021

    • Author(s)
      Shun-ichi Amari, Jimmy Ba, Roger Grosse, Xuechen Li, Atsushi Nitanda, Taiji Suzuki, Denny Wu, Ji Xu
    • Journal Title

      ICLR2021

      Volume: 9

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Selective inference for latent block models2021

    • Author(s)
      Watanabe Chihiro、Suzuki Taiji
    • Journal Title

      Electronic Journal of Statistics

      Volume: 15 Issue: 1 Pages: 3137-3183

    • DOI

      10.1214/21-ejs1853

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-20H00576, KAKENHI-PROJECT-18H03201
  • [Journal Article] Decomposable-Net: Scalable Low-Rank Compression for Neural Networks2021

    • Author(s)
      Yaguchi Atsushi、Suzuki Taiji、Nitta Shuhei、Sakata Yukinobu、Tanizawa Akiyuki
    • Journal Title

      Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

      Volume: 13 Pages: 3249-3256

    • DOI

      10.24963/ijcai.2021/447

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Quantitative Understanding of VAE as a Non-linearly Scaled Isometric Embedding2021

    • Author(s)
      Akira Nakagawa, Keizo Kato, Taiji Suzuki
    • Journal Title

      ICML2021, Proceedings of Machine Learning Research

      Volume: 139

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning2021

    • Author(s)
      Tomoya Murata, Taiji Suzuki
    • Journal Title

      ICML2021, Proceedings of Machine Learning Research

      Volume: 139

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Statistical Theory of Deep Learning2021

    • Author(s)
      鈴木 大慈
    • Journal Title

      Journal of the Japan Statistical Society, Japanese Issue

      Volume: 50 Issue: 2 Pages: 229-256

    • DOI

      10.11329/jjssj.50.229

    • NAID

      130007995093

    • ISSN
      0389-5602, 2189-1478
    • Year and Date
      2021-03-05
    • Language
      Japanese
    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Goodness-of-fit test for latent block models2021

    • Author(s)
      Watanabe Chihiro、Suzuki Taiji
    • Journal Title

      Computational Statistics & Data Analysis

      Volume: 154 Pages: 107090-107090

    • DOI

      10.1016/j.csda.2020.107090

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201, KAKENHI-PROJECT-20H00576
  • [Journal Article] On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting2021

    • Author(s)
      Akiyama Shunta、Suzuki Taiji
    • Journal Title

      Proceedings of the 38th International Conference on Machine Learning, PMLR

      Volume: 139 Pages: 152-162

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Journal Article] Differentiable Multiple Shooting Layers2021

    • Author(s)
      Stefano Massaroli, Michael Poli, Sho Sonoda, Taiji Suzuki, Jinkyoo Park, Atsushi Yamashita, Hajime Asama
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 34

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods2021

    • Author(s)
      Taiji Suzuki, Shunta Akiyama
    • Journal Title

      ICLR2020

      Volume: 9

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Particle Dual Averaging: Optimization of Mean Field Neural Networks with Global Convergence Rate Analysis2021

    • Author(s)
      Atsushi Nitanda, Denny Wu, Taiji Suzuki
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 34

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Exponential Convergence Rates of Classification Errors on Learning with SGD and Random Features2021

    • Author(s)
      Shingo Yashima, Atsushi Nitanda, Taiji Suzuki
    • Journal Title

      AISTATS2021, Proceedings of Machine Learning Research

      Volume: 130

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Sharp characterization of optimal minibatch size for stochastic finite sum convex optimization2021

    • Author(s)
      Nitanda Atsushi, Murata Tomoya, Suzuki Taiji
    • Journal Title

      Knowledge and Information Systems

      Volume: 63 Issue: 9 Pages: 2513-2539

    • DOI

      10.1007/s10115-021-01593-1

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-19K20337, KAKENHI-PROJECT-18H03201
  • [Journal Article] Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space2021

    • Author(s)
      Taiji Suzuki, Atsushi Nitanda
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 34

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Graph Neural Networks Exponentially Lose Expressive Power for Node Classification2020

    • Author(s)
      Kenta Oono, Taiji Suzuki
    • Journal Title

      Proceedings of Eighth International Conference on Learning Representations

      Volume: - Pages: 1-37

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics2020

    • Author(s)
      Suzuki Taiji
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 33 Pages: 19224-19237

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Journal Article] Graph Neural Networks Exponentially Lose Expressive Power for Node Classification2020

    • Author(s)
      Kenta Oono, Taiji Suzuki
    • Journal Title

      ICLR2020

      Volume: 8

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Functional Gradient Boosting for Learning Residual-like Networks with Statistical Guarantees2020

    • Author(s)
      Atsushi Nitanda, Taiji Suzuki
    • Journal Title

      Proceedings of Machine Learning Research

      Volume: 108 Pages: 2981-2991

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] Independently Interpretable Lasso for Generalized Linear Models2020

    • Author(s)
      Takada Masaaki、Suzuki Taiji、Fujisawa Hironori
    • Journal Title

      Neural Computation

      Volume: 32 Issue: 6 Pages: 1168-1221

    • DOI

      10.1162/neco_a_01279

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network2020

    • Author(s)
      Taiji Suzuki, Hiroshi Abe, Tomoaki Nishimura
    • Journal Title

      ICLR2020

      Volume: 8

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Compression based Bound for Non-Compressed Network: Unified Generalization Error Analysis of Large Compressible Deep Neural Network2020

    • Author(s)
      Taiji Suzuki, Hiroshi Abe, Tomoaki Nishimura
    • Journal Title

      Proceedings of Eighth International Conference on Learning Representations

      Volume: - Pages: 1-34

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] Functional Gradient Boosting for Learning Residual-like Networks with Statistical Guarantees2020

    • Author(s)
      Atsushi Nitanda, Taiji Suzuki
    • Journal Title

      AISTATS2020, Proceedings of Machine Learning Research

      Volume: 108

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Bayesian optimization design for dose‐finding based on toxicity and efficacy outcomes in phase I/ II clinical trials2020

    • Author(s)
      Takahashi Ami、Suzuki Taiji
    • Journal Title

      Pharmaceutical Statistics

      Volume: 20(3) Issue: 3 Pages: 422-439

    • DOI

      10.1002/pst.2085

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint2020

    • Author(s)
      Jimmy Ba, Murat Erdogdu, Taiji Suzuki, Denny Wu, Tianzong Zhang
    • Journal Title

      ICLR2020

      Volume: 8

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics2020

    • Author(s)
      Taiji Suzuki
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 33

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Understanding Generalization in Deep Learning via Tensor Methods2020

    • Author(s)
      Jingling Li, Yanchao Sun, Jiahao Su, Taiji Suzuki, Furong Huang
    • Journal Title

      Proceedings of Machine Learning Research

      Volume: 108 Pages: 504-515

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks2020

    • Author(s)
      Kenta Oono, Taiji Suzuki
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 33

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint2020

    • Author(s)
      Jimmy Ba, Murat Erdogdu, Taiji Suzuki, Denny Wu, Tianzong Zhang
    • Journal Title

      Proceedings of Eighth International Conference on Learning Representations

      Volume: - Pages: 1-40

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] A reproducing kernel Hilbert space approach to high dimensional partially varying coefficient model2020

    • Author(s)
      Lv Shaogao、Fan Zengyan、Lian Heng、Suzuki Taiji、Fukumizu Kenji
    • Journal Title

      Computational Statistics & Data Analysis

      Volume: 152 Pages: 107039-107039

    • DOI

      10.1016/j.csda.2020.107039

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Domain Adaptation Regularization for Spectral Pruning2020

    • Author(s)
      Laurent Dillard, Yosuke Shinya, Taiji Suzuki
    • Journal Title

      BMVC2020 (British Machine Vision Conference 2020)

      Volume: 31

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] On the minimax optimality and superiority of deep neural network learning over sparse parameter spaces2020

    • Author(s)
      Satoshi Hayakawa and Taiji Suzuki
    • Journal Title

      Neural Networks

      Volume: 123 Pages: 343-361

    • DOI

      10.1016/j.neunet.2019.12.014

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201, KAKENHI-PROJECT-15H05707
  • [Journal Article] Understanding of Generalization in Deep Learning via Tensor Methods2020

    • Author(s)
      Jingling Li, Yanchao Sun, Ziyin Liu, Taiji Suzuki and Furong Huang
    • Journal Title

      AISTATS2020, Proceedings of Machine Learning Research

      Volume: 108

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] 数理工学とAI2020

    • Author(s)
      鈴木大慈
    • Journal Title

      数理科学

      Volume: 685

    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Understanding the Effects of Pre-Training for Object Detectors via Eigenspectrum2019

    • Author(s)
      Shinya Yosuke、Simo-Serra Edgar、Suzuki Taiji
    • Journal Title

      Proceedings of 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

      Volume: - Pages: 1931-1941

    • DOI

      10.1109/iccvw.2019.00242

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] UVTON: UV Mapping to Consider the 3D Structure of a Human in Image-Based Virtual Try-On Network2019

    • Author(s)
      Kubo Shizuma、Iwasawa Yusuke、Suzuki Masahiro、Matsuo Yutaka
    • Journal Title

      Proceedings of 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

      Volume: - Pages: 3105-3108

    • DOI

      10.1109/iccvw.2019.00375

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] Sharp Characterization of Optimal Minibatch Size for Stochastic Finite Sum Convex Optimization2019

    • Author(s)
      Nitanda Atsushi、Murata Tomoya、Suzuki Taiji
    • Journal Title

      2019 IEEE International Conference on Data Mining (ICDM)

      Volume: なし Pages: 488-497

    • DOI

      10.1109/icdm.2019.00059

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201, KAKENHI-PROJECT-15H05707
  • [Journal Article] Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality2019

    • Author(s)
      Taiji Suzuki
    • Journal Title

      he 7th International Conference on Learning Representations (ICLR2019)

      Volume: 7

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Stochastic Gradient Descent with Exponential Convergence Rates of Expected Classification Errors2019

    • Author(s)
      Atsushi Nitanda, Taiji Suzuki
    • Journal Title

      Proceedings of Machine Learning Research (AISTATS2019)

      Volume: 89

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Stochastic Gradient Descent with Exponential Convergence Rates of Expected Classification Errors2019

    • Author(s)
      Atsushi Nitanda, Taiji Suzuki
    • Journal Title

      Proceedings of Machine Learning Research (AISTATS2019)

      Volume: 89 Pages: 1417-1426

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] Cross-domain Recommendation via Deep Domain Adaptation2019

    • Author(s)
      Heishiro Kanagawa, Hayato Kobayashi, Nobuyuki Shimizu, Yukihiro Tagami, and Taiji Suzuki
    • Journal Title

      Advances in Information Retrieval 41st European Conference on IR Research, ECIR 2019

      Volume: なし

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Approximation and Non-parametric Estimation of ResNet-type Convolutional Neural Networks2019

    • Author(s)
      Kenta Oono and Taiji Suzuki
    • Journal Title

      Proceedings of Machine Learning Research (ICML2019)

      Volume: 97

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Understanding the Effects of Pre-training for Object Detectors via Eigenspectrum2019

    • Author(s)
      Yosuke Shinya, Edgar Simo-Serra, and Taiji Suzuki
    • Journal Title

      ICCV2019, Neural Architects Workshop

      Volume: なし

    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Approximation and Non-Parametric Estimation of ResNet-type Convolutional Neural Networks2019

    • Author(s)
      Kenta Oono, Taiji Suzuki
    • Journal Title

      ICML2019, Proceedings of Machine Learning Research

      Volume: 97 Pages: 4922-4931

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] Stochastic Optimization for Machine Learning2018

    • Author(s)
      鈴木 大慈
    • Journal Title

      Bulletin of the Japan Society for Industrial and Applied Mathematics

      Volume: 28 Issue: 3 Pages: 27-33

    • DOI

      10.11540/bjsiam.28.3_27

    • NAID

      130007552778

    • ISSN
      2432-1982
    • Year and Date
      2018-09-26
    • Language
      Japanese
    • Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Independently Interpretable Lasso: A New Regularizer for Sparse Regression with Uncorrelated Variables2018

    • Author(s)
      Masaaki Takada, Taiji Suzuki, Hironori Fujisawa
    • Journal Title

      Proceedings of Machine Learning Research (AISTATS2018)

      Volume: 84 Pages: 454-463

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Journal Article] Functional Gradient Boosting based on Residual Network Perception2018

    • Author(s)
      Atsushi Nitanda and Taiji Suzuki
    • Journal Title

      Proceedings of Machine Learning Research (ICML2018)

      Volume: 80

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Fast generalization error bound of deep learning from a kernel perspective2018

    • Author(s)
      T. Suzuki
    • Journal Title

      Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics, in PMLR

      Volume: 84 Pages: 1397-1406

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] Trimmed Density Ratio Estimation2018

    • Author(s)
      S. Liu, A. Takeda, T. Suzuki and K. Fukumizu
    • Journal Title

      Advances in Neural Information Processing Systems 30

      Volume: - Pages: 4521-4531

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative Models2018

    • Author(s)
      A. Nitanda and T. Suzuki
    • Journal Title

      Proceedings of Machine Learning Research

      Volume: Vol.84 Pages: 1008-1016

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] Fast generalization error bound of deep learning from a kernel perspective2018

    • Author(s)
      Taiji Suzuki
    • Journal Title

      Proceedings of Machine Learning Research (AISTATS2018)

      Volume: 84 Pages: 1397-1406

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Journal Article] Statistical Learning Theory and Its Application to Deep Learning2018

    • Author(s)
      鈴木 大慈
    • Journal Title

      Bulletin of the Japan Society for Industrial and Applied Mathematics

      Volume: 28 Issue: 4 Pages: 28-33

    • DOI

      10.11540/bjsiam.28.4_28

    • NAID

      130007621094

    • ISSN
      2432-1982
    • Year and Date
      2018-12-21
    • Language
      Japanese
    • Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Fast generalization error bound of deep learning from a kernel perspective2018

    • Author(s)
      Taiji Suzuki
    • Journal Title

      AISTATS2018, Proceedings of Machine Learning Research

      Volume: 84

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18K19793
  • [Journal Article] Functional gradient boosting based on residual network perception2018

    • Author(s)
      Atsushi Nitanda and Taiji Suzuki
    • Journal Title

      Proceedings of the 35th International Conference on Machine Learning: PMLR

      Volume: 80:

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18K19793
  • [Journal Article] 「機械学習と数理統計」~統計的学習理論を通じて~2018

    • Author(s)
      鈴木大慈
    • Journal Title

      数理科学

      Volume: 662

    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization2018

    • Author(s)
      T. Murata and T. Suzuki
    • Journal Title

      Advances in Neural Information Processing Systems 30

      Volume: - Pages: 608-617

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] Generalization Error Analysis of Gaussian Process Regression via Theories of Reproducing Kernel Hilbert Spaces2018

    • Author(s)
      鈴木 大慈
    • Journal Title

      SYSTEMS, CONTROL AND INFORMATION

      Volume: 62 Issue: 10 Pages: 396-404

    • DOI

      10.11509/isciesci.62.10_396

    • NAID

      130007632579

    • ISSN
      0916-1600, 2424-1806
    • Year and Date
      2018-10-15
    • Language
      Japanese
    • Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative Models2018

    • Author(s)
      A. Nitanda, T. Suzuki
    • Journal Title

      Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics, in PMLR

      Volume: 84 Pages: 1008-1016

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] Hunt for the tipping point during endocrine resistance process in breast cancer by dynamic network biomarkers2018

    • Author(s)
      Rui Liu, Jinzeng Wang, Masao Ukai, Ki Sewon, Pei Chen, Yutaka Suzuki, Haiyun Wang, Kazuyuki Aihara, Mariko Okada-Hatakeyama, Luonan Chen
    • Journal Title

      Journal of Molecular Cell Biology

      Volume: - Issue: 8 Pages: 1-16

    • DOI

      10.1093/jmcb/mjy059

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PLANNED-17H06302, KAKENHI-PROJECT-18H04031, KAKENHI-PROJECT-15H05707
  • [Journal Article] Adam Induces Implicit Weight Sparsity in Rectifier Neural Networks2018

    • Author(s)
      Atsushi Yaguchi, Taiji Suzuki, Wataru Asano, Shuhei Nitta, Yukinobu Sakata, Akiyuki Tanizawa
    • Journal Title

      Proceedings of IEEE 17th International Conference on Machine Learning and Applications (ICMLA 2018)

      Volume: * Pages: 17-20

    • DOI

      10.1109/icmla.2018.00054

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Journal Article] Fast generalization error bound of deep learning from a kernel perspective2018

    • Author(s)
      Taiji Suzuki
    • Journal Title

      Proceedings of Machine Learning Research (AISTATS2018)

      Volume: 84

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Generalized ridge estimator and model selection criteria in multivariate linear regression2018

    • Author(s)
      Mori Yuichi、Suzuki Taiji
    • Journal Title

      Journal of Multivariate Analysis

      Volume: 165 Pages: 243-261

    • DOI

      10.1016/j.jmva.2017.12.006

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PLANNED-25120012, KAKENHI-PROJECT-25730013, KAKENHI-PROJECT-18H03201, KAKENHI-PROJECT-15H05707
  • [Journal Article] Independently Interpretable Lasso: A New Regularizer for Sparse Regression with Uncorrelated Variables2018

    • Author(s)
      Masaaki Takada, Taiji Suzuki, and Hironori Fujisawa
    • Journal Title

      Proceedings of Machine Learning Research (AISTATS2018)

      Volume: 84

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Independently Interpretable Lasso: A New Regularizer for Sparse Regression with Uncorrelated Variables2018

    • Author(s)
      M. Takada, T. Suzuki, H. Fujisawa
    • Journal Title

      Proceedings of Machine Learning Research

      Volume: Vol.84 Pages: 454-463

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation2018

    • Author(s)
      T. Murata, and T. Suzuki
    • Journal Title

      Advances in Neural Information Processing Systems 31 (NeurIPS2018)

      Volume: - Pages: 5312-5321

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] Independently Interpretable Lasso: A New Regularizer for Sparse Regression with Uncorrelated Variables2018

    • Author(s)
      M. Takada, T. Suzuki, H. Fujisawa
    • Journal Title

      Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics, in PMLR

      Volume: 84 Pages: 454-463

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative Models2018

    • Author(s)
      Atsushi Nitanda, Taiji Suzuki
    • Journal Title

      Proceedings of Machine Learning Research (AISTATS2018)

      Volume: 84 Pages: 1008-1016

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Journal Article] 数理のクロスロード/機械学習の数理/(1) 深層学習の理論2018

    • Author(s)
      鈴木大慈
    • Journal Title

      数学セミナー

      Volume: 685

    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Fast generalization error bound of deep learning from a kernel perspective2018

    • Author(s)
      T. Suzuki
    • Journal Title

      Proceedings of Machine Learning Research

      Volume: Vol.84 Pages: 1397-1406

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] Short-term local weather forecast using dense weather station by deep neural network2018

    • Author(s)
      Yonekura Kazuo、Hattori Hitoshi、Suzuki Taiji
    • Journal Title

      2018 IEEE International Conference on Big Data (Big Data)

      Volume: 1 Pages: 10-13

    • DOI

      10.1109/bigdata.2018.8622195

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201, KAKENHI-PROJECT-26280009, KAKENHI-PROJECT-15H05707
  • [Journal Article] Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation2018

    • Author(s)
      Tomoya Murata, and Taiji Suzuki
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 31

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Journal Article] Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative Models2018

    • Author(s)
      Atsushi Nitanda and Taiji Suzuki
    • Journal Title

      Proceedings of Machine Learning Research (AISTATS2018)

      Volume: 84

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Functional Gradient Boosting based on Residual Network Perception2018

    • Author(s)
      A. Nitanda, T. Suzuki
    • Journal Title

      Proceedings of the 35th International Conference on Machine Learning

      Volume: Vol.80 Pages: 3819-3828

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Journal Article] Fast Learning Rate of Non-Sparse Multiple Kernel Learning and Optimal Regularization Strategies2018

    • Author(s)
      Taiji Suzuki
    • Journal Title

      Electronic Journal of Statistics

      Volume: 印刷中

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Journal Article] Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative Models2018

    • Author(s)
      Atsushi Nitanda and Taiji Suzuki
    • Journal Title

      AISTATS2018, Proceedings of Machine Learning Research

      Volume: 84

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18K19793
  • [Journal Article] Overfitting and Regularization2018

    • Author(s)
      鈴木 大慈
    • Journal Title

      Bulletin of the Japan Society for Industrial and Applied Mathematics

      Volume: 28 Issue: 2 Pages: 28-33

    • DOI

      10.11540/bjsiam.28.2_28

    • NAID

      130007490723

    • ISSN
      2432-1982
    • Year and Date
      2018-06-26
    • Language
      Japanese
    • Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation2018

    • Author(s)
      Tomoya Murata, and Taiji Suzuki
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 31

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Adam Induces Implicit Weight Sparsity in Rectifier Neural Networks2018

    • Author(s)
      Yaguchi Atsushi、Suzuki Taiji、Asano Wataru、Nitta Shuhei、Sakata Yukinobu、Tanizawa Akiyuki
    • Journal Title

      IEEE International Conference on Machine Learning and Applications (ICMLA)

      Volume: 17

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Fast learning rate of non-sparse multiple kernel learning and optimal regularization strategies2018

    • Author(s)
      Suzuki Taiji
    • Journal Title

      Electronic Journal of Statistics

      Volume: 12 Issue: 2 Pages: 2141-2192

    • DOI

      10.1214/18-ejs1399

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201, KAKENHI-PROJECT-26280009, KAKENHI-PROJECT-15H05707
  • [Journal Article] 数理のクロスロード/機械学習の数理/(2) カーネル法とニューラルネットワーク2018

    • Author(s)
      鈴木大慈
    • Journal Title

      数学セミナー

      Volume: 686

    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Overview of Machine Learning2018

    • Author(s)
      鈴木 大慈
    • Journal Title

      Bulletin of the Japan Society for Industrial and Applied Mathematics

      Volume: 28 Issue: 1 Pages: 32-37

    • DOI

      10.11540/bjsiam.28.1_32

    • NAID

      130007386557

    • ISSN
      2432-1982
    • Year and Date
      2018-03-23
    • Language
      Japanese
    • Open Access
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Journal Article] Support Consistency of Direct Sparse-Change Learning in Markov Networks2017

    • Author(s)
      Song Liu, Taiji Suzuki, Relator Raissa, Jun Sese, Masashi Sugiyama, and Kenji Fukumizu
    • Journal Title

      The Annals of Statistics

      Volume: 印刷中

    • NAID

      110009971454

    • Peer Reviewed / Acknowledgement Compliant
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Journal Article] Trimmed Density Ratio Estimation2017

    • Author(s)
      Song Liu, Akiko Takeda, Taiji Suzuki and Kenji Fukumizu
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 30 Pages: 4518-4528

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Journal Article] Support consistency of direct sparse-change learning in Markov networks2017

    • Author(s)
      Liu Song、Suzuki Taiji、Relator Raissa、Sese Jun、Sugiyama Masashi、Fukumizu Kenji
    • Journal Title

      The Annals of Statistics

      Volume: 45 Issue: 3 Pages: 959-990

    • DOI

      10.1214/16-aos1470

    • NAID

      110009971454

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013, KAKENHI-PROJECT-15H05707
  • [Journal Article] Trimmed Density Ratio Estimation2017

    • Author(s)
      Liu, S., Takeda, A., Suzuki, T. and Fukumizu, K.
    • Journal Title

      Advances in Neural Information Processing Systems (NIPS 2017)

      Volume: 30

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] Learning sparse structural changes in high-dimensional Markov networks2017

    • Author(s)
      Song Liu, Kenji Fukumizu, and Taiji Suzuki
    • Journal Title

      Behaviormetrika

      Volume: 44(1) Issue: 1 Pages: 265-286

    • DOI

      10.1007/s41237-017-0014-z

    • Peer Reviewed / Acknowledgement Compliant / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PLANNED-25120012, KAKENHI-PROJECT-15H06823, KAKENHI-PROJECT-25730013
  • [Journal Article] Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization2017

    • Author(s)
      T. Murata, T. Suzuki
    • Journal Title

      Advances in Neural Information Processing Systems (NIPS2017)

      Volume: 30

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization2017

    • Author(s)
      Tomoya Murata and Taiji Suzuki
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 30 Pages: 608-617

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Journal Article] Stochastic Difference of Convex Algorithm and its Application to Training Deep Boltzmann Machines2017

    • Author(s)
      Atsushi Nitanda, Taiji Suzuki
    • Journal Title

      Proceedings of Machine Learning Research (AISTATS2017)

      Volume: 54 Pages: 470-478

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Journal Article] Task-dependent recurrent dynamics in visual cortex2017

    • Author(s)
      Tajima Satohiro、Koida Kowa、Tajima Chihiro I、Suzuki Hideyuki、Aihara Kazuyuki、Komatsu Hidehiko
    • Journal Title

      eLife

      Volume: 6

    • DOI

      10.7554/elife.26868

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PLANNED-15H05916, KAKENHI-PLANNED-15H05917, KAKENHI-PROJECT-17H00892, KAKENHI-PROJECT-15H05707
  • [Journal Article] Support Consistency of Direct Sparse-Change Learning in Markov Networks2016

    • Author(s)
      Song Liu, Suzuki Taiji, Raissa Relator, Jun Sese, Masashi Sugiyama, and Kenji Fukumizu
    • Journal Title

      Annals of Statistics

      Volume: 2016 Pages: 34-34

    • NAID

      110009971454

    • Peer Reviewed / Acknowledgement Compliant
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] Support consistency of direct sparse-change learning in Markov networks2016

    • Author(s)
      Liu, S., Suzuki, T., Raissa, R., Sese, J., Sugiyama, M., Fukumizu, K.
    • Journal Title

      The Annals of Statistics

      Volume: 印刷中

    • NAID

      110009971454

    • Peer Reviewed / Acknowledgement Compliant / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H01678
  • [Journal Article] Gaussian process nonparametric tensor estimator and its minimax optimality2016

    • Author(s)
      Heishiro Kanagawa, Taiji Suzuki, Hayato Kobayashi, Nobuyuki Shimizu, Yukihiro Tagami
    • Journal Title

      Proceedings of The 33rd International Conference on Machine Learning

      Volume: - Pages: 1632-1641

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] System Identification and Parameter Estimation in Mathematical Medicine: Examples Demonstrated for Prostate Cancer2016

    • Author(s)
      Yoshito Hirata, Kai Morino, Taiji Suzuki, Qian Guo, Hiroshi Fukuhara, and Kazuyuki Aihara
    • Journal Title

      Quantitative Biology

      Volume: 4(1) Issue: 1 Pages: 13-19

    • DOI

      10.1007/s40484-016-0059-0

    • Peer Reviewed / Acknowledgement Compliant / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013, KAKENHI-PLANNED-25120012, KAKENHI-PROJECT-15H05707, KAKENHI-PROJECT-26280009
  • [Journal Article] Structure Learning of Partitioned Markov Networks2016

    • Author(s)
      Song Liu, Taiji Suzuki, Masashi Sugiyama, and Kenji Fukumizu
    • Journal Title

      Proceedings of Machine Learning Research (The 33rd International Conference on Machine Learning)

      Volume: 48 Pages: 439-448

    • Peer Reviewed / Acknowledgement Compliant / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Journal Article] Structure Learning of Partitioned Markov Networks2016

    • Author(s)
      Song Liu, Taiji Suzuki , Masashi Sugiyama, Kenji Fukumizu
    • Journal Title

      Proceedings of The 33rd International Conference on Machine Learning

      Volume: - Pages: 439-448

    • Peer Reviewed / Acknowledgement Compliant / Open Access
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] Bayes method for low rank tensor estimation2016

    • Author(s)
      Taiji Suzuki and Heishiro Kanagawa
    • Journal Title

      Journal of Physics: Conference Series: International Meeting on ”High-Dimensional Data Driven Science” (HD3-2015)

      Volume: 699(1) Pages: 012020-012020

    • DOI

      10.1088/1742-6596/699/1/012020

    • Peer Reviewed / Acknowledgement Compliant / Open Access
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] Flattening the Density Gradient for Eliminating Spatial Centrality to Reduce Hubness2016

    • Author(s)
      Hara, K., Suzuki, I., Kobayashi, K., Fukumizu, K. and Radovanovic, M.
    • Journal Title

      Proc. 30th AAAI Conference on Artificial Intelligence

      Volume: 1 Pages: 1659-1665

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Journal Article] Structure Learning of Partitioned Markov Networks2016

    • Author(s)
      Song Liu, Taiji Suzuki, Masashi Sugiyama, and Kenji Fukumizu
    • Journal Title

      Proc. 33rd International Conference on Machine Learning

      Volume: 1 Pages: 1-9

    • Peer Reviewed / Acknowledgement Compliant / Open Access
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] Minimax Optimal Alternating Minimization for Kernel Nonparametric Tensor Learning2016

    • Author(s)
      Taiji Suzuki, Heishiro Kanagawa, Hayato Kobayashi, Nobuyuki Shimizu, and Yukihiro Tagami
    • Journal Title

      Proceedings of the 30th Annual Conference on Neural Information Processing Systems (NIPS2016)

      Volume: 30 Pages: 3783-3791

    • Peer Reviewed / Acknowledgement Compliant / Open Access
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Journal Article] Gaussian process nonparametric tensor estimator and its minimax optimality2016

    • Author(s)
      Heishiro Kanagawa, Taiji Suzuki, Hayato Kobayashi, Nobuyuki Shimizu, and Yukihiro Tagami
    • Journal Title

      Proceedings of Machine Learning Research (The 33rd International Conference on Machine Learning)

      Volume: 48 Pages: 1632-1641

    • Peer Reviewed / Acknowledgement Compliant / Open Access
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Journal Article] A Consistent Method for Graph Based Anomaly Localization2015

    • Author(s)
      Satoshi Hara, Tetsuro Morimura, Toshihiro Takahashi, Hiroki Yanagisawa, Taiji Suzuki
    • Journal Title

      JMLR Workshop and Conference Proceedings

      Volume: 38

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Journal Article] Stochastic Alternating Direction Method of Multipliers for Structured Regularization2015

    • Author(s)
      Taiji Suzuki
    • Journal Title

      Journal of Japan Society of Computational Statistics

      Volume: 28

    • NAID

      130005434004

    • Peer Reviewed / Acknowledgement Compliant
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Journal Article] Support Consistency of Direct Sparse-Change Learning in Markov Networks2015

    • Author(s)
      Song Liu, Taiji Suzuki, and Masashi Sugiyama
    • Journal Title

      Proceedigs of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI2015)

      Volume: 1 Pages: 2785-2791

    • NAID

      110009971454

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Journal Article] Localized Centering: Reducing Hubness in Large-Sample Data2015

    • Author(s)
      K. Hara, I. Suzuki, M. Shimbo, K. Kobayashi, K. Fukumizu, and M. Radomanovic
    • Journal Title

      Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence

      Volume: 1 Pages: 2645-2651

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Journal Article] Stochastic Alternating Direction Method of Multipliers for Structured Regularization2015

    • Author(s)
      Taiji Suzuki
    • Journal Title

      Journal of Japan Society of Computational Statistics

      Volume: 28 Pages: 105-124

    • NAID

      130005434004

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Journal Article] Convergence rate of Bayesian tensor estimator and its minimax optimality2015

    • Author(s)
      Taiji Suzuki
    • Journal Title

      JMLR Workshop and Conference Proceedings:The 32nd International Conference on Machine Learning (ICML2015)

      Volume: 37 Pages: 1273-1282

    • Peer Reviewed / Acknowledgement Compliant / Open Access
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] Stochastic Alternating Direction Method of Multipliers for Structured Regularization2015

    • Author(s)
      Taiji Suzuki
    • Journal Title

      Journal of Japan Society of Computational Statistics

      Volume: 28 Pages: 105-124

    • NAID

      130005434004

    • Peer Reviewed / Acknowledgement Compliant
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] A Consistent Method for Graph Based Anomaly Localization2015

    • Author(s)
      Satoshi Hara, Tetsuro Morimura, Toshihiro Takahashi, Hiroki Yanagisawa, Taiji Suzuki
    • Journal Title

      Journal of Machine Learning Research, Workshop & Conference Proceedings (ICML2014)

      Volume: 38 Pages: 333-341

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] Stochastic alternating direction method of multipliers for structured regularization2015

    • Author(s)
      Suzuki, T.
    • Journal Title

      Journal of Japan Society of Computational Statistics

      Volume: 28 Pages: 105-124

    • NAID

      130005434004

    • Peer Reviewed / Acknowledgement Compliant / Open Access
    • Data Source
      KAKENHI-PROJECT-15H01678
  • [Journal Article] Stochastic Dual Coordinate Ascent with Alternating Direction Method of Multipliers2014

    • Author(s)
      Taiji Suzuki
    • Journal Title

      JMLR Workshop and Conference Proceedings

      Volume: 32 Pages: 736-744

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Journal Article] Ryota Tomioka, and Taiji Suzuki: Convex Tensor Decomposition via Structured Schatten Norm Regularization.2014

    • Author(s)
      Tomioka, R. and Suzuki, T.
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 26 Pages: 1331-1339

    • Peer Reviewed
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] Support Consistency of Direct Sparse-Change Learning in Markov Networks2014

    • Author(s)
      Song Liu, Taiji Suzuki, and Masashi Sugiyama
    • Journal Title

      The Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI2015)

      Volume: 1 Pages: 2785-2791

    • NAID

      110009971454

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] 凸最適化に基づくテンソル分解2014

    • Author(s)
      冨岡亮太,鈴木大慈,林浩平,鹿島久嗣
    • Journal Title

      応用数理

      Volume: 24 Pages: 16-23

    • NAID

      110009900559

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Journal Article] Stochastic Dual Coordinate Ascent with Alternating Direction Method of Multipliers2014

    • Author(s)
      Taiji Suzuki
    • Journal Title

      Journal of Machine Learning Research, Workshop and Conference Proceedings

      Volume: 32 Pages: 736-744

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Journal Article] Computational complexity of kernel-based density-ratio estimation: A condition number analysis2013

    • Author(s)
      Takafumi Kanamori, Taiji Suzuki, and Masashi Sugiyama
    • Journal Title

      Machine Learning

      Volume: 90 Issue: 3 Pages: 431-460

    • DOI

      10.1007/s10994-012-5323-6

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-22700289, KAKENHI-PROJECT-24300106, KAKENHI-PROJECT-24500340
  • [Journal Article] Density-difference estimation2013

    • Author(s)
      M. Sugiyama, T. Suzuki, T. Kanamori, M. C. du Plessis, S. Liu, and I. Takeuchi
    • Journal Title

      Neural Computation

      Volume: 25 Issue: 10 Pages: 2734-2775

    • DOI

      10.1162/neco_a_00492

    • NAID

      110009588474

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-23300069, KAKENHI-PROJECT-24500340, KAKENHI-PROJECT-25730013
  • [Journal Article] Fast learning rate of multiple kernel learning: trade-off between sparsity and smoothness2013

    • Author(s)
      Taiji Suzuki, and Masashi Sugiyama
    • Journal Title

      The Annals of Statistics

      Volume: 41 Issue: 3

    • DOI

      10.1214/13-aos1095

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Journal Article] Fast learning rate ofmultiple kernel learning:trade-off between sparsity and smoothness2013

    • Author(s)
      Taiji Suzuki, and Masashi
    • Journal Title

      The Annals of Statistics

    • Data Source
      KAKENHI-PROJECT-22700289
  • [Journal Article] Relative Density-Ratio Estimation for Robust Distribution Comparison2013

    • Author(s)
      Makoto Yamada, Taiji Suzuki, Takafumi Kanamori, Hirotaka Hachiya, and Masashi Sugiyama
    • Journal Title

      Neural Computation

      Volume: 25 Issue: 5 Pages: 1324-1370

    • DOI

      10.1162/neco_a_00442

    • NAID

      10031099905

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-22700289, KAKENHI-PROJECT-24500340
  • [Journal Article] Sufficient dimension reduction via squared-loss mutual information estimation2013

    • Author(s)
      Taiji Suzuki, and Masashi Sugiyama
    • Journal Title

      Neural Computation

      Volume: vol. 25 Pages: 725-758

    • NAID

      130008079589

    • Data Source
      KAKENHI-PROJECT-22700289
  • [Journal Article] Nonlinear System Identification for Prostate Cancer and Optimality of Intermittent Androgen Suppression Therapy2013

    • Author(s)
      Taiji Suzuki, and Kazuyuki Aihara
    • Journal Title

      Mathematical Biosciences

      Volume: 245 Issue: 1 Pages: 40-48

    • DOI

      10.1016/j.mbs.2013.04.007

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Journal Article] Computational complexity of kernel-based density-ratio estimation2013

    • Author(s)
      Takafumi Kanamori, Taiji Suzuki, and Masashi Sugiyama
    • Journal Title

      A condition number analysis. Machine Learning

      Volume: vol.90 Pages: 431-460

    • Data Source
      KAKENHI-PROJECT-22700289
  • [Journal Article] Improvement of multiple kernel learning using adaptively weighted regularization2013

    • Author(s)
      Taiji Suzuki
    • Journal Title

      JSIAM Letters

      Volume: 5 Issue: 0 Pages: 49-52

    • DOI

      10.14495/jsiaml.5.49

    • NAID

      130003371122

    • ISSN
      1883-0609, 1883-0617
    • Language
      English
    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Journal Article] Statistical analysis of kernel-based least-squares density-ratio estimation2012

    • Author(s)
      Takafumi Kanamori, Taiji Suzuki, and Masashi Sugiyama
    • Journal Title

      Machine Learning

      Volume: 86 Issue: 3 Pages: 335-367

    • DOI

      10.1007/s10994-011-5266-3

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Journal Article] f-divergence estimation and two-sample homogeneity test under semiparametric density-ratio models2012

    • Author(s)
      Takafumi Kanamori, Taiji Suzuki, and Masashi Sugiyama
    • Journal Title

      IEEE Transactions on Information Theory

      Volume: 58 Issue: 2 Pages: 708-720

    • DOI

      10.1109/tit.2011.2163380

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Journal Article] A Fast Algorithm for Multiple Kernel Learning with Thousands of Kernels2011

    • Author(s)
      Taiji Suzuki and Ryota Tomioka: SpicyMKL
    • Journal Title

      Machine Learning

      Volume: vol. 85, issue 1 Pages: 77-108

    • Data Source
      KAKENHI-PROJECT-22700289
  • [Journal Article] Direct density-ratio estimation with dimensionality reduction via least-squares hetero-distributional subspace search2011

    • Author(s)
      Masashi Sugiyama, Makoto Yamada, Paul von Bunau, Taiji Suzuki, Takafumi Kanamori, Motoaki Kawanabe
    • Journal Title

      Neural Networks

      Volume: 24 Pages: 183-198

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Journal Article] SpicyMKL: A Fast Algorithm for Multiple Kernel Learning with Thousands of Kernels2011

    • Author(s)
      Taiji Suzuki and Ryota Tomioka
    • Journal Title

      DOI 10.1007/s10994-011-5252-9

      Volume: 85 Issue: 1-2 Pages: 77-108

    • DOI

      10.1007/s10994-011-5252-9

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-22700138, KAKENHI-PROJECT-22700289
  • [Journal Article] Least-squares Independent Component Analysis2011

    • Author(s)
      Taiji Suzuki, Masashi Sugiyama
    • Journal Title

      Neural Computation

      Volume: 23 Pages: 284-301

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Journal Article] Super-Linear Convergence of Dual Augmented Lagrangian Algorithm for Sparse Learning2011

    • Author(s)
      Ryota Tomioka, Taiji Suzuki, and Masashi Sugiyama
    • Journal Title

      Journal of Machine Learning Research

      Volume: 12 Pages: 1537-1586

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Journal Article] Least-Squares Two-Sample Test2011

    • Author(s)
      Masashi Sugiyama, Taiji Suzuki, Yuta Itoh, and Takafumi Kanamori
    • Journal Title

      Neural Networks

      Volume: 24 Issue: 7 Pages: 735-751

    • DOI

      10.1016/j.neunet.2011.04.003

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Journal Article] Density ratio matching under the Bregman divergence: A unified framework of density ratio estimation2011

    • Author(s)
      Masashi Sugiyama, Taiji Suzuki, and Takafumi Kanamori
    • Journal Title

      Annals of the Institute of Statistical Mathematics

      Volume: 11 Issue: 5 Pages: 1-36

    • DOI

      10.1007/s10463-011-0343-8

    • NAID

      40019382740

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-22700289, KAKENHI-PROJECT-24300106, KAKENHI-PROJECT-24500340
  • [Journal Article] Theoretical analysis of density ratio estimation2010

    • Author(s)
      Takafumi Kanamori, Taiji Suzuki, Masashi Sugiyama
    • Journal Title

      IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

      Volume: E93-A Pages: 787-798

    • NAID

      10026863929

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Journal Article] Piecewise Affine Systems Modelling for Optimizing Hormonal Therapy of Prostate Cancer2010

    • Author(s)
      Taiji Suzuki, Nicholas Bruchovsky, Kazuyuki Aihara
    • Journal Title

      Philosophical Transactions A of the Royal Society

      Volume: 368 Pages: 5045-5059

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Journal Article] On prior selection and covariate shift ofbeta-Bayesian prediction under alpha-divergence risk.2010

    • Author(s)
      Taiji Suzuki, and Fumiyasu Komaki
    • Journal Title

      Communications in Statistics --- Theory and Methods

      Volume: 39(8) Pages: 1655-1673

    • Data Source
      KAKENHI-PROJECT-22700289
  • [Journal Article] On prior selection and covariate shift of $¥beta$-Bayesian prediction under $¥alpha$-divergence risk2010

    • Author(s)
      Taiji Suzuki, Fumiyasu Komaki
    • Journal Title

      Communications in Statistics---Theory and Methods

      Volume: 39 Pages: 1655-1673

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Journal Article] Relative Density-Ratio Estimation for Robust Distribution Comparison

    • Author(s)
      Makoto Yamada,Taiji Suzuki,Takafumi Kanamori, Hirotaka Hachiya, Masashi Sugiyama
    • Journal Title

      Neural Computation

    • NAID

      10031099905

    • Data Source
      KAKENHI-PROJECT-22700289
  • [Patent] 気象予測システム、気象予測方法、および気象予測プログラム2018

    • Inventor(s)
      米倉一男,鈴木大慈
    • Industrial Property Rights Holder
      米倉一男,鈴木大慈
    • Industrial Property Rights Type
      特許
    • Industrial Property Number
      2018-227904
    • Filing Date
      2018
    • Overseas
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Patent] 気象予測システム、気象予測方法、および気象予測プログラム2018

    • Inventor(s)
      米倉一男 ,鈴木大慈
    • Industrial Property Rights Holder
      株式会社 IHI,国立大学法人東京大学
    • Industrial Property Rights Type
      特許
    • Industrial Property Number
      2018-227904
    • Filing Date
      2018
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] Convergence of mean field Langevin dynamics and its application to neural network optimization2024

    • Author(s)
      Taiji Suzuki
    • Organizer
      The Mathematics of Data
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Presentation] Feature learning via mean field neural networks and anisotropic features2023

    • Author(s)
      Taiji Suzuki, Denny Wu, Atsushi Nitanda and Kazusato Oko
    • Organizer
      International Symposium on Recent Advances in Theories and Methodologies for Large Complex Data
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Presentation] 高次元データ学習における特徴学習の優位性2022

    • Author(s)
      鈴木大慈
    • Organizer
      科研費シンポジウム「大規模複雑データの理論と方法論~新たな発展と関連分野への応用~」
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Presentation] Deep learning theory from feature learning perspective2022

    • Author(s)
      Taiji Suzuki
    • Organizer
      The 14th Asian Conference on Machine Learning (Keynote talk)
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Presentation] 深層学習の数理2022

    • Author(s)
      鈴木大慈
    • Organizer
      日本数学会企画特別講演
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] AutoLL: Automatic Linear Layout of Graphs based on Deep Neural Network2021

    • Author(s)
      Watanabe C., Suzuki T.
    • Organizer
      IEEE Symposium Series on Computational Intelligence
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Presentation] Optimization and statistical efficiency of neural network in mean field regimes2021

    • Author(s)
      Taiji Suzuki
    • Organizer
      Workshop on Functional Inference and Machine Intelligence
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Deep Learning Theory and Optimization (Tutorial talk)2021

    • Author(s)
      Suzuki T.
    • Organizer
      The 13th Asian Conference on Machine Learning
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Presentation] Benefit of deep learning: Efficiency of function estimation and its optimization guarantee2021

    • Author(s)
      Taiji Suzuki
    • Organizer
      KSIAM2021 (Special Session: CJK-SIAM mini-symposium I: Emerging Mathematics in AI)
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 深層ニューラルネットワークの近似理論と適応能力2021

    • Author(s)
      鈴木大慈
    • Organizer
      数値解析セミナー
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] CGから実写への転移学習におけるスケーリング則2021

    • Author(s)
      Hiroaki Mikami, Kenji Fukumizu, Shogo Murai, Shuji Suzuki, Yuta Kikuchi, Taiji Suzuki, Shin-ichi Maeda, Kohei Hayashi
    • Organizer
      第24回情報論的学習理論ワークショップ
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Benefit of deep learning: Statistical efficiency and optimization guarantee with non-convex noisy gradient descent2021

    • Author(s)
      Taiji Suzuki
    • Organizer
      Statistics Seminar at University of Bristol
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] リンク予測におけるバイアス項によるグラフニューラルネットワークの表現力強化2021

    • Author(s)
      長谷川 貴大,鈴木 大慈
    • Organizer
      2021年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error2021

    • Author(s)
      Taiji Suzuki, Hiroshi Abe, Tomoya Murata, Shingo Horiuchi, Kotaro Ito, Tokuma Wachi, So Hirai, Masatoshi Yukishima, Tomoaki Nishimura
    • Organizer
      Twenty-Ninth International Joint Conference on Artificial Intelligence
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization2021

    • Author(s)
      大古 一聡, 鈴木 大慈, 二反田 篤史, Wenny Wu
    • Organizer
      第24回情報論的学習理論ワークショップ
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Recent theoretical developments about statistical and optimization efficiency of deep learning2021

    • Author(s)
      Taiji Suzuki
    • Organizer
      First Australia-Japan Workshop on Machine Learning
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Optimality and superiority of deep learning for estimating functions in variants of Besov spaces2021

    • Author(s)
      Taiji Suzuki, Atsushi Nitanda, and Kazuma Tsuji
    • Organizer
      4th International Conference on Econometrics and Statistics (EcoSta2021)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 平均場ニューラルネットワークの効率的最適化法2021

    • Author(s)
      二反田 篤史,大古 一聡,Denny Wu,鈴木 大慈
    • Organizer
      2021年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Deep Learning Theory and Optimization2021

    • Author(s)
      Taiji Suzuki
    • Organizer
      Tutorial talk, The Online Asian Machine Learning School (OAMLS), The 13th Asian Conference on Machine Learning (ACML2021)
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 多層ニューラルネットワークモデルに基づくmatrix reordering2021

    • Author(s)
      渡邊千紘, 鈴木大慈
    • Organizer
      第24回情報論的学習理論ワークショップ
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 深層学習の理論2021

    • Author(s)
      鈴木大慈
    • Organizer
      言語処理学会第27回年次大会(NLP2021)
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] ノイズ付き勾配法を用いた教師生徒設定における二層ReLuニューラルネットワークの学習2021

    • Author(s)
      秋山俊太, 鈴木大慈
    • Organizer
      第24回情報論的学習理論ワークショップ
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 教師生徒設定における勾配法による二層ReLU ニューラルネットワークの学習可能性について2021

    • Author(s)
      秋山 俊太,鈴木 大慈
    • Organizer
      2021年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 深層学習の理論解析:非線形性と最適化動力学2021

    • Author(s)
      鈴木大慈
    • Organizer
      『非線形動力学に基づく次世代AIと基盤技術』に関するシンポジウム
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] ResNetのモデル圧縮手法の提案および圧縮誤差理論解析2021

    • Author(s)
      平川 雅人,鈴木 大慈
    • Organizer
      2021年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Deep Learning Theory from Statistics to Optimization2021

    • Author(s)
      Taiji Suzuki
    • Organizer
      Tutorial talk, The 6th Asian Conference on Pattern Recognition (ACPR2021)
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Understanding Generalization in Deep Learning via Tensor Methods2020

    • Author(s)
      Jingling Li, Yanchao Sun, Jiahao Su, Taiji Suzuki, Furong Huang
    • Organizer
      Twenty Third International Conference on Artificial Intelligence and Statistics
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] Statistical efficiency and optimization of deep learning from the view point of non-convexity2020

    • Author(s)
      Taiji Suzuki
    • Organizer
      "AI + Math" Colloquia, Institute of Natural Sciences, Shanghai Jiao Tong University
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] マルチスケールグラフニューラルネットの勾配ブースティング法による解析2020

    • Author(s)
      大野 健太, 鈴木 大慈
    • Organizer
      第23回情報論的学習理論ワークショップ (IBIS2020)
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 無限次元勾配ランジュバン動力学による深層学習の最適化理論と汎化誤差解析2020

    • Author(s)
      鈴木大慈
    • Organizer
      九州大学統計科学セミナー
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Graph Neural Networks Exponentially Lose Expressive Power for Node Classification2020

    • Author(s)
      Kenta Oono, Taiji Suzuki
    • Organizer
      Eighth International Conference on Learning Representations
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] 深層学習の数理:カーネル法,スパース推定との接点2020

    • Author(s)
      鈴木大慈
    • Organizer
      画像の認識・理解シンポジウム MIRU2020
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 深層学習の最適化と汎化誤差:非凸性の観点から2020

    • Author(s)
      鈴木大慈
    • Organizer
      物性研究所短期研究会 「量子多体計算と第一原理計算の新展開」(FQCS2020)
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 無限次元勾配ランジュバン動力学によるニューラルネットワークの最適化理論と汎化誤差解析2020

    • Author(s)
      鈴木 大慈
    • Organizer
      2020年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Latent Block Modelのブロック構造に関する選択的推論2020

    • Author(s)
      渡邊 千紘,鈴木 大慈
    • Organizer
      2020年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Statistical efficiency and optimization of deep learning from the viewpoint of non-convexity2020

    • Author(s)
      Taiji Suzuki
    • Organizer
      Math Machine Learning seminar MPI MIS + UCLA
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 変動指数Besov空間の回帰問題に対する深層学習の推定誤差解析2020

    • Author(s)
      辻 和真,鈴木 大慈
    • Organizer
      2020年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 機械学習における最適化理論と学習理論的側面2020

    • Author(s)
      鈴木大慈
    • Organizer
      第17回組合せ最適化セミナー
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Compression based Bound for Non-Compressed Network: Unified Generalization Error Analysis of Large Compressible Deep Neural Network2020

    • Author(s)
      Taiji Suzuki, Hiroshi Abe, Tomoaki Nishimura
    • Organizer
      Eighth International Conference on Learning Representations
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] Statistical efficiency and optimization of deep learning from the view point of non-convexity2020

    • Author(s)
      Taiji Suzuki
    • Organizer
      Applied Mathematics and Computation Seminar at UMass Amherst
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 深層学習の数理:カーネル法,スパース推定との接点2020

    • Author(s)
      鈴木大慈
    • Organizer
      画像の認識・理解シンポジウム MIRU2020
    • Invited
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Presentation] Functional Gradient Boosting for Learning Residual-like Networks with Statistical Guarantees2020

    • Author(s)
      Atsushi Nitanda, Taiji Suzuki
    • Organizer
      Twenty Third International Conference on Artificial Intelligence and Statistics
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] 再生核ヒルベルト空間上の非凸最適化問題に対する勾配ランジュバン動力学の収束誤差解析2020

    • Author(s)
      佐藤 寛司,鈴木 大慈
    • Organizer
      2020年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 変動指数Besov 空間の回帰問題に対する深層学習の推定誤差解析2020

    • Author(s)
      辻 和真, 鈴木 大慈
    • Organizer
      第23回情報論的学習理論ワークショップ (IBIS2020)
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 無限次元勾配ランジュバン動力学による深層学習の最適化と汎化誤差解析2020

    • Author(s)
      鈴木大慈
    • Organizer
      第23回情報論的学習理論ワークショップ (IBIS2020)
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 勾配ブースティング法を用いたマルチスケールグラフニューラルネットの学習とその最適化・汎化性能解析2020

    • Author(s)
      大野 健太,鈴木 大慈
    • Organizer
      2020年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 無限次元勾配ランジュバン動力学による深層学習の最適化と汎化誤差解析2020

    • Author(s)
      鈴木大慈
    • Organizer
      第23回情報論的学習理論ワークショップ
    • Invited
    • Data Source
      KAKENHI-PROJECT-20H00576
  • [Presentation] Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint2020

    • Author(s)
      Jimmy Ba, Murat Erdogdu, Taiji Suzuki, Denny Wu, Tianzong Zhang
    • Organizer
      Eighth International Conference on Learning Representations
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] 粒子双対平均化法:平均場ニューラルネットワークの大域的収束保証付最適化法2020

    • Author(s)
      二反田 篤史, Denny Wu, 鈴木 大慈
    • Organizer
      第23回情報論的学習理論ワークショップ (IBIS2020)
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 確率的勾配降下法のNTK理論による最適収束率2020

    • Author(s)
      二反田 篤史,鈴木 大慈
    • Organizer
      2020年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Fast learning rate of neural tangent kernel learning and nonconvex optimization by infinite dimensional Langevin dynamics in RKHS2020

    • Author(s)
      Taiji Suzuki
    • Organizer
      Workshop on Functional Inference and Machine Intelligence
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 数学で解き明かす深層学習の原理2020

    • Author(s)
      鈴木大慈
    • Organizer
      CREST・さきがけ・AIMaP合同シンポジウム『数学パワーが世界を変える』
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] カーネル法におけるrandom featureを用いた確率的勾配法の期待識別誤差の線形収束性2019

    • Author(s)
      八嶋晋吾, 二反田 篤史, 鈴木大慈
    • Organizer
      2019年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Bayesian optimization for dose finding studies2019

    • Author(s)
      高橋亜実, 鈴木大慈
    • Organizer
      2019年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Random Featureを用いた確率的勾配法の期待識別誤差の収束解析2019

    • Author(s)
      八嶋晋吾, 二反田篤史, 鈴木大慈
    • Organizer
      IBIS2019
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Understanding the Effects of Pre-Training for Object Detectors via Eigenspectrum2019

    • Author(s)
      Yosuke Shinya, Edgar Simo-Serra, Taiji Suzuki
    • Organizer
      2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] Generalization error of deep learning with connection to sparse estimation in function space2019

    • Author(s)
      Taiji Suzuki
    • Organizer
      Workshop on Functional Inference and Machine Intelligence
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] グラフスペクトルを介した深層グラフモデルの漸近挙動解析2019

    • Author(s)
      大野健太, 鈴木大慈
    • Organizer
      2019年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Adaptivity of Deep Learning in Besov Space with its Connection to Sparse Estimation2019

    • Author(s)
      Taiji Suzuki
    • Organizer
      Third International Workshop on Symbolic-Neural Learning (SNL-2019)
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] Toward Understanding Expressive Power of Graph Convolutional Neural Networks2019

    • Author(s)
      Kenta Oono, Taiji Suzuki
    • Organizer
      Data Science, Statistics & Visualization (DSSV2019)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 深層ニューラルネットワークの適応能力:関数空間におけるスパース推定との接点2019

    • Author(s)
      鈴木大慈
    • Organizer
      武蔵野大学数理工学シンポジウム2019
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Generalization error of deep learning with connection to sparse estimation in function space2019

    • Author(s)
      Taiji Suzuki:
    • Organizer
      Workshop on Functional Inference and Machine Intelligence
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18K19793
  • [Presentation] 深層ニューラルネットワークの適応能力と汎化誤差解析2019

    • Author(s)
      鈴木大慈
    • Organizer
      AIMaPワークショップ「非ノイマン型計算、理論と応用」
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 深層ニューラルネットワークの圧縮可能性を用いた非圧縮ネットワークの汎化誤差解析2019

    • Author(s)
      鈴木大慈
    • Organizer
      2019年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Sharp Characterization of Optimal Minibatch Size for Stochastic Finite Sum Convex Optimization2019

    • Author(s)
      Atsushi Nitanda, Tomoya Murata, Taiji Suzuki
    • Organizer
      The 19th IEEE International Conference on Data Mining
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] スパースなパラメータ空間における深層ニューラルネットワークのミニマックス最適性および優位性について2019

    • Author(s)
      早川知志, 鈴木大慈
    • Organizer
      2019年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Compression Based Bound for Non-compressed Deep Neural Network Models and Their Data Adaptivity2019

    • Author(s)
      Taiji Suzuki
    • Organizer
      Data Science, Statistics & Visualization (DSSV2019)
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] 深層学習における汎化誤差理論とその応用および非凸確率的最適化2019

    • Author(s)
      鈴木大慈
    • Organizer
      第七回数理ファイナンス合宿型セミナー
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Generalization error of deep learning and its learning dynamics from compression ability point of view2019

    • Author(s)
      Taiji Suzuki
    • Organizer
      The 11th Innovation with Statistics and Data Science (ICSA 2019)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Estimation ability of deep learning with connection to sparse estimation in function space2019

    • Author(s)
      Taiji Suzuki
    • Organizer
      4TU AMI annual event Mathematics of Deep Learning
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Generalization error bound of deep learning via spectral analysis and its application to model compression2019

    • Author(s)
      Taiji Suzuki
    • Organizer
      3rd International Conference on Econometrics and Statistics (EcoSta2019)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 識別問題に対する高次元二層ニューラルネットの勾配法による汎化性能解析2019

    • Author(s)
      二反田 篤史, 鈴木大慈
    • Organizer
      2019年度統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Compressing deep neural network and its generalization error analysis via kernel theory2019

    • Author(s)
      Taiji Suzuki
    • Organizer
      Reinforcement Learning & Biological Intelligence, learning from biology, learning for biology
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Compression Based Bound for Non-compressed Deep Neural Network Models and Their Data Adaptivity2019

    • Author(s)
      Taiji Suzuki
    • Organizer
      Data Science, Statistics & Visualization (DSSV2019)
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Exponential Convergence of Stochastic Gradient Descent for Binary Classification Problems2019

    • Author(s)
      Atsushi Nitanda, Taiji Suzuki
    • Organizer
      Data Science, Statistics & Visualization (DSSV2019)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 深層ニューラルネットワークの適応能力:関数空間におけるスパース推定との接点2019

    • Author(s)
      鈴木大慈
    • Organizer
      第9回 脳型人工知能とその応用ミニワークショップ
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Compressing deep neural network and its generalization error analysis via kernel theory2019

    • Author(s)
      Taiji Suzuki
    • Organizer
      Reinforcement Learning & Biological Intelligence, learning from biology, learning for biology
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18K19793
  • [Presentation] Adaptivity of deep learning in Besov space with its connection to sparse estimation2019

    • Author(s)
      Taiji Suzuki
    • Organizer
      Third International Workshop on Symbolic-Neural Learning (SNL-2019)
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Approximation and Non-Parametric Estimation of ResNet-type Convolutional Neural Networks2019

    • Author(s)
      Kenta Oono, Taiji Suzuki
    • Organizer
      Thirty-sixth International Conference on Machine Learning (ICML2019)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] Latent Block Modelのクラスタ数に関する適合度検定2019

    • Author(s)
      渡邊千紘, 鈴木大慈
    • Organizer
      IBIS2019
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 深層ニューラルネットワークの汎化誤差とそのスパース推定との接点2019

    • Author(s)
      鈴木大慈
    • Organizer
      応用統計ワークショップ
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Generalization analysis and optimization of deep learning: adaptivity and kernel view2019

    • Author(s)
      Taiji Suzuki
    • Organizer
      EPFL Machile Learning Seminer
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 高次元二層ニューラルネットに対する勾配降下法による識別誤差の大域収束性と汎化性能解析2019

    • Author(s)
      二反田篤史, 鈴木大慈
    • Organizer
      IBIS2019
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Adaptivity of deep ReLU network and its generalization error analysis2019

    • Author(s)
      Taiji Suzuki
    • Organizer
      The Second Korea-Japan Machine Learning Workshop
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Stochastic Gradient Descent with Exponential Convergence Rates of Expected Classification Errors2019

    • Author(s)
      Atsushi Nitanda, Taiji Suzuki
    • Organizer
      The 22nd International Conference on Artificial Intelligence and Statistics
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] UVTON: UV Mapping to Consider the 3D Structure of a Human in Image-Based Virtual Try-On Network2019

    • Author(s)
      Shizuma Kubo, Yusuke Iwasawa, Masahiro Suzuki, Yutaka Matsuo
    • Organizer
      2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] Introduction to machine learning and deep learning theories: statistics and optimization2019

    • Author(s)
      Taiji Suzuki
    • Organizer
      4th International Symposium on Research and Education of Computational Science (RECS2019)
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Besov空間における深層学習の汎化誤差解析およびモデル解析への応用2019

    • Author(s)
      鈴木大慈
    • Organizer
      愛媛大学理学部理学科数学・数理情報コース数学談話会
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 深層学習における高次元性2019

    • Author(s)
      鈴木大慈
    • Organizer
      金融工学・数理計量ファイナンスの諸問題 2019
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 機械学習の現状と深層学習の数理2018

    • Author(s)
      鈴木大慈
    • Organizer
      山形大学データサイエンス推進室キックオフミーティング
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 統計・機械学習における確率的最適化2018

    • Author(s)
      鈴木大慈
    • Organizer
      統計数理研究所公開講座
    • Invited
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Presentation] 深層学習のカーネル法による汎化誤差解析とその適応能力の評価2018

    • Author(s)
      鈴木大慈
    • Organizer
      京都大学数学教室・数理解析研究所談話会
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Generalization Error and Compressibility of Deep Learning via Kernel Analysis2018

    • Author(s)
      Taiji Suzuki
    • Organizer
      Tokyo Deep Learning Workshop (Deep Learning: Theory, Algorithms, and Applications)
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] Functional gradient boosting based on residual network perception2018

    • Author(s)
      A. Nitanda and T. Suzuki
    • Organizer
      35th International Conference on Machine Learning (ICML2018)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] 機械学習における構造を利用した確率的最適化技法2018

    • Author(s)
      鈴木大慈
    • Organizer
      2018年電子情報通信学会基礎・境界ソサイエティ大会大会
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 確率的勾配降下法による期待識別誤差の線形収束性2018

    • Author(s)
      二反田 篤史,鈴木 大慈
    • Organizer
      統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 機械学習における構造を利用した確率的最適化技法2018

    • Author(s)
      鈴木大慈
    • Organizer
      2018年電子情報通信学会基礎・境界ソサイエティ大会大会
    • Invited
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Presentation] 機械学習・人工知能における数学の役割2018

    • Author(s)
      鈴木大慈
    • Organizer
      2018年度数学教育学会春季年会,総合講演1
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Short-term local weather forecast using dense weather station by deep neural network2018

    • Author(s)
      K. Yonekura, H. Hattori, T. Suzuki
    • Organizer
      2018 IEEE International Conference on Big Data
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] 深層学習の統計的学習理論:カーネル法とウェーブレット解析による視点2018

    • Author(s)
      鈴木大慈
    • Organizer
      第3回統計・機械学習若手シンポジウム「統計・機械学習の交わりと拡がり」
    • Invited
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Presentation] Generalization Error and Compressibility of Deep Learning via Kernel Analysis2018

    • Author(s)
      Taiji Suzuki
    • Organizer
      Tokyo Deep Learning Workshop (Deep Learning: Theory, Algorithms, and Applications)
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Generalization Error and Compressibility of Deep Learning via Kernel Analysis2018

    • Author(s)
      Taiji Suzuki
    • Organizer
      Tokyo Deep Learning Workshop (Deep Learning: Theory, Algorithms, and Applications)
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 統計学と機械学習,そして人工知能2018

    • Author(s)
      鈴木 大慈
    • Organizer
      統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Accelerated stochastic optimization for finite sum regularized empirical risk minimization2018

    • Author(s)
      Taiji Suzuki
    • Organizer
      First Conference on Discrete Optimization and Machine Learning
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 深層学習の統計的学習理論:カーネル法とウェーブレット解析による視点2018

    • Author(s)
      鈴木大慈
    • Organizer
      第3回統計・機械学習若手シンポジウム「統計・機械学習の交わりと拡がり」
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Adaptivity of Deep ReLU Network for Learning in Besov Spaces.2018

    • Author(s)
      Taiji Suzuki
    • Organizer
      Forum "Math-for-Industry" 2018 - Big Data Analysis, AI, Fintech, Math in Finances and Economics
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18K19793
  • [Presentation] Sparse Modeling with Uncorrelated Variables2018

    • Author(s)
      Masaaki Takada, Taiji Suzuki and Hironori Fujisawa
    • Organizer
      統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation2018

    • Author(s)
      T. Murata and T. Suzuki
    • Organizer
      Thirty-second Conference on Neural Information Processing Systems (NeurIPS2018)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] Generalization error analysis of deep learning: avoiding curse of dimensionality and practical application2018

    • Author(s)
      Taiji Suzuki
    • Organizer
      統計関連学会連合大会,2018 CSA-KSS-JSS Joint International Sessions: Machine Learning
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Estimating nonlinear tensor product in infinite dimensional functional space by kernel and neural network models2018

    • Author(s)
      Taiji Suzuki
    • Organizer
      IMS-APRM2018
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Adaptivity of Deep ReLU Network for Learning in Besov Spaces2018

    • Author(s)
      Taiji Suzuki
    • Organizer
      Forum "Math-for-Industry" 2018 - Big Data Analysis, AI, Fintech, Math in Finances and Economics -
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 人工知能・機械学習における課題,数学の役割と期待について2018

    • Author(s)
      鈴木大慈
    • Organizer
      日本数学会2018年度年会,数学連携ワークショップ「Society 5.0と数学---量子コンピュータと人工知能を題材に---」
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Fast generalization error bound of deep learning from a kernel perspective2018

    • Author(s)
      T. Suzuki
    • Organizer
      The 21st International Conference on Artificial Intelligence and Statistics (AISTATS2018)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative Models2018

    • Author(s)
      A. Nitanda and T. Suzuki
    • Organizer
      The 21st International Conference on Artificial Intelligence and Statistics (AISTATS2018)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] 機械学習の現状と深層学習の数理2018

    • Author(s)
      鈴木大慈
    • Organizer
      山形大学データサイエンス推進室キックオフミーティング
    • Invited
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Presentation] 深層学習の汎化誤差理論とそのモデル解析への応用2018

    • Author(s)
      鈴木大慈
    • Organizer
      2018年日本数学会秋季総合分科会
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 機械学習技術の進展とその数理基盤2018

    • Author(s)
      鈴木大慈
    • Organizer
      数理システムユーザーコンファレンス 2017
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 深層学習の汎化誤差理論とモデル圧縮への応用2018

    • Author(s)
      鈴木 大慈
    • Organizer
      「人工知能を用いた統合的ながん医療システムの開発」CRESTセミナー
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 強低ノイズ条件下識別問題に対する確率的勾配降下法の線形収束性2018

    • Author(s)
      二反田 篤史,鈴木 大慈
    • Organizer
      IBIS2018
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] 統計・機械学習における確率的最適化2018

    • Author(s)
      鈴木大慈
    • Organizer
      統計数理研究所公開講座
    • Invited
    • Data Source
      KAKENHI-PROJECT-18H03201
  • [Presentation] Independently Interpretable Lasso: A New Regularizer for Sparse Regression with Uncorrelated Variables2018

    • Author(s)
      M. Takada, T. Suzuki, H. Fujisawa
    • Organizer
      The 21st International Conference on Artificial Intelligence and Statistics (AISTATS2018)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] Generalization error bounds of deep learning by Bayesian and empirical risk minimization approaches from a kernel perspective2017

    • Author(s)
      Taiji Suzuki
    • Organizer
      France/Japan Machine Learning Workshop
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 関数微分法による深層ニューラルネットワークの構築2017

    • Author(s)
      二反田篤史,鈴木大慈
    • Organizer
      IBIS2017
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Generalization error bound of Bayesian deep learning: a kernel perspective2017

    • Author(s)
      Taiji Suzuki
    • Organizer
      2017 Probabilistic Graphical Model Workshop: Structure, Sparsity and High-dimensionality
    • Place of Presentation
      東京
    • Year and Date
      2017-02-22
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] Doubly Accelerated Stochastic Variance Reduced Gradient Method for Regularized Empirical Risk Minimization2017

    • Author(s)
      Tomoya Murata, Taiji Suzuki
    • Organizer
      第28回IBISML研究会
    • Place of Presentation
      東京工業大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] A stochastic optimization method and generalization bounds for voting classifiers by continuous density functions2017

    • Author(s)
      Atsushi Nitanda, Taiji Suzuki
    • Organizer
      第28回IBISML研究会
    • Place of Presentation
      東京工業大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Generalization error analysis of deep learning and its application to network structure determination2017

    • Author(s)
      Taiji Suzuki
    • Organizer
      French-Japanese Workshop on Deep Learning and Artificial Intelligence
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] AIと機械学習の現状,および医療現場での可能性と限界について2017

    • Author(s)
      鈴木大慈
    • Organizer
      第53回日本医学放射線学会秋季臨床大会
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization2017

    • Author(s)
      T. Murata and T. Suzuki
    • Organizer
      Neural Information Processing Systems (NIPS 2017)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] 機械学習と深層学習技術,高次元機械学習手法2017

    • Author(s)
      鈴木大慈
    • Organizer
      生命ダイナミクスの理解とその応用:数理科学的アプローチ 玉原ワークショップ2017
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 高次元機械学習手法の統計的学習理論と計算理論2017

    • Author(s)
      鈴木大慈
    • Organizer
      統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] カーネル法の理論による深層学習の汎化誤差解析2017

    • Author(s)
      鈴木大慈
    • Organizer
      大規模統計モデリングと計算統計 IV
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Generalization error analysis of deep learning via a kernel perspective2017

    • Author(s)
      Taiji Suzuki
    • Organizer
      統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 深層リカレントニューラルネットワークを用いたfMRIの解析及び脳機能の解読2017

    • Author(s)
      大橋耕也,鈴木大慈
    • Organizer
      第28回IBISML研究会
    • Place of Presentation
      東京工業大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 構造のある機械学習問題における最適化技法2017

    • Author(s)
      鈴木大慈
    • Organizer
      第29回RAMPシンポジウム, 企画セッション「機械学習と最適化」
    • Invited
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] カーネル法による深層学習の汎化誤差理論2017

    • Author(s)
      鈴木大慈
    • Organizer
      JST ERATO 河原林巨大グラフプロジェクト,情報系 WINTER FESTA Episode3
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Trimmed Density Ratio Estimation2017

    • Author(s)
      S. Liu, A. Takeda, T. Suzuki and K. Fukumizu
    • Organizer
      Neural Information Processing Systems (NIPS 2017)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] 輸送写像による確率測度の最適化とその応用2017

    • Author(s)
      二反田 篤史, 鈴木 大慈
    • Organizer
      統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 構造のある機械学習問題における最適化技法2017

    • Author(s)
      鈴木大慈,二反田篤史,村田智也
    • Organizer
      第29回RAMPシンポジウム
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Generalization error analysis of deep learning and its application to network structure determination2017

    • Author(s)
      Taiji Suzuki
    • Organizer
      French-Japanese Workshop on Deep Learning and Artificial Intelligence
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] 相関情報を罰則項に導入したスパースモデリング2017

    • Author(s)
      髙田正彬, 鈴木大慈, 藤澤洋徳
    • Organizer
      IBIS2017
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 機械学習技術の進展とその数理基盤2017

    • Author(s)
      鈴木大慈
    • Organizer
      数理システムユーザーコンファレンス
    • Invited
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] Estimation accuracy and computational efficiency of non-parametric kernel tensor estimators2017

    • Author(s)
      Taiji Suzuki
    • Organizer
      The 10th International Conference of the ERCIM WG on Computational and Methodological Statistics (CMStatistics 2017)
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Generalization error bound of Bayesian deep learning: a kernel perspective2017

    • Author(s)
      Taiji Suzuki
    • Organizer
      Probabilistic Graphical Model Workshop: Structure, Sparsity and High-dimensionality
    • Place of Presentation
      Tachikawa, Japan
    • Year and Date
      2017-02-22
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Gaussian process nonparametric tensor estimator and its minimax optimality2016

    • Author(s)
      Heishiro Kanagawa, Taiji Suzuki, Hayato Kobayashi, Nobuyuki Shimizu, Yukihiro Tagami
    • Organizer
      The 33rd International Conference on Machine Learning
    • Place of Presentation
      New York
    • Year and Date
      2016-06-20
    • Int'l Joint Research
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] 多変量正規分布におけるミニマックス性をもつベイズ予測分布のクラスと線形回帰への応用2016

    • Author(s)
      森裕一,鈴木大慈
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      金沢大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 統計・機械学習における確率的最適化2016

    • Author(s)
      鈴木大慈
    • Organizer
      統計数理研究所公開講座
    • Place of Presentation
      統計数理研究所
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 低ランクテンソルの学習理論と計算理論2016

    • Author(s)
      鈴木大慈
    • Organizer
      IBIS2016
    • Place of Presentation
      京都大学
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Some convergence results of nonparametric tensor estimators2016

    • Author(s)
      Taiji Suzuki
    • Organizer
      International Symposium on Statistical Analysis for Large Complex Data
    • Place of Presentation
      Tsukuba University, Japan
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 正則化項付き期待誤差最小化問題に対する加速AdaGradの提案2016

    • Author(s)
      村田智也,鈴木大慈
    • Organizer
      IBIS2016
    • Place of Presentation
      京都大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Particle Mirror Descent for the Infinite Majority Vote Classifier2016

    • Author(s)
      Atsushi Nitanda, Taiji Suzuki
    • Organizer
      IBIS2016
    • Place of Presentation
      京都大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Statistical performance and computational efficiency of low rank tensor estimators2016

    • Author(s)
      Taiji Suzuki
    • Organizer
      Probabilistic Graphical Model Workshop: Sparsity, Structure and High-dimensionality
    • Place of Presentation
      Tachikawa, Tokyo, Japan
    • Year and Date
      2016-03-23
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] ノンパラメトリックテンソルの推定理論と計算理論2016

    • Author(s)
      鈴木大慈
    • Organizer
      大規模統計モデリングと計算統計III
    • Place of Presentation
      東京大学駒場キャンパス
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 深層学習による画像特徴抽出の自己位置推定への応用2016

    • Author(s)
      千葉龍一郎,鈴木大慈
    • Organizer
      IBIS2016
    • Place of Presentation
      京都大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Partitioned Markov Networks2016

    • Author(s)
      Song Liu, Taiji Suzuki , Masashi Sugiyama, Kenji Fukumizu
    • Organizer
      MIRU2016 第19回画像の認識・理解シンポジウム
    • Place of Presentation
      浜松
    • Invited
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] 確率的DCアルゴリズムと深層ボルツマンマシン学習への応用2016

    • Author(s)
      二反田篤史,鈴木大慈
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      金沢大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] ニュース・動画サービス間のクロスドメイン推薦における課題2016

    • Author(s)
      金川平志郎,小林隼人,清水伸幸,田頭幸浩,鈴木 大慈
    • Organizer
      IBIS2016
    • Place of Presentation
      京都大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] コンピューターが学び賢くなる-人工知能のための数学-2016

    • Author(s)
      鈴木大慈
    • Organizer
      第19回JST数学キャラバン
    • Place of Presentation
      岡山大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 確率的交互方向乗数法とマルチクラスグラフ型正則化学習への応用2016

    • Author(s)
      鈴木大慈
    • Organizer
      統計学と機械学習における数理とモデリング
    • Place of Presentation
      東京工業大学大岡山キャンパス
    • Year and Date
      2016-02-21
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 統計・計算理論 で広がる機械学習2016

    • Author(s)
      鈴木大慈
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      金沢大学
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Structure Learning of Partitioned Markov Networks2016

    • Author(s)
      Song Liu, Taiji Suzuki, Masashi Sugiyama, and Kenji Fukumizu
    • Organizer
      33rd International Conference on Machine Learning
    • Place of Presentation
      New York
    • Year and Date
      2016-06-19
    • Int'l Joint Research
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] 発展する機械学習と統計分野の関わりそして今後について2016

    • Author(s)
      鈴木大慈
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      金沢大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Structure Learning of Partitioned Markov Networks2016

    • Author(s)
      Song Liu, Taiji Suzuki , Masashi Sugiyama, Kenji Fukumizu
    • Organizer
      The 33rd International Conference on Machine Learning
    • Place of Presentation
      New York
    • Year and Date
      2016-06-20
    • Int'l Joint Research
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] 確率的交互方向乗数法の理論と応用2016

    • Author(s)
      鈴木大慈
    • Organizer
      日本オペレーションズ・リサーチ学会, 最適化の基礎とフロンティア研究会
    • Place of Presentation
      東京理科大学神楽坂キャンパス森戸記念館
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Statistical Performance and Computational Efficiency of Nonparametric Low Rank Tensor Estimators2016

    • Author(s)
      Taiji Suzuki
    • Organizer
      The First Korea-Japan Machine Learning Symposium
    • Place of Presentation
      Seoul, Japan
    • Year and Date
      2016-06-02
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 確率の不思議と機械学習2016

    • Author(s)
      鈴木大慈
    • Organizer
      第8回マスフェスタ(全国数学生徒研究発表会)
    • Place of Presentation
      京都大学
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Statistical Performance and Computational Efficiency of Nonparametric Low Rank Tensor Estimators2016

    • Author(s)
      Taiji Suzuki
    • Organizer
      2016 International Workshop on Spatial and Temporal Modeling from Statistical, Machine Learning and Engineering perspectives (STM2016)
    • Place of Presentation
      Tachikawa, Japan
    • Year and Date
      2016-06-20
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 低ランクテンソル推定におけるベイズ推定量の性質2015

    • Author(s)
      鈴木大慈
    • Organizer
      第9回日本統計学会春季集会
    • Place of Presentation
      東京
    • Year and Date
      2015-03-08
    • Invited
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Presentation] Bayes Method for Low Rank Tensor Estimation2015

    • Author(s)
      Taiji Suzuki
    • Organizer
      International Meeting on High-Dimensional Data Driven Science (HD3-2015)
    • Place of Presentation
      Mielparque Kyoto, Kyoto, Japan
    • Year and Date
      2015-12-14
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H05707
  • [Presentation] ガウシアンプロセスカーネル法による非線形テンソル学習およびマルチタスク学習への応用2015

    • Author(s)
      金川平志郎,鈴木大慈
    • Organizer
      情報論的学習理論ワークショップ(IBIS2015)
    • Place of Presentation
      エポカルつくば
    • Year and Date
      2015-11-27
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] スパース推定の数理:統計理論から計算手法まで2015

    • Author(s)
      鈴木大慈
    • Organizer
      日本応用数理学会, 三部会連携「応用数理セミナー」
    • Place of Presentation
      東京大学本郷キャンパス
    • Year and Date
      2015-12-24
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 確率的最適化から始める機械学習入門2015

    • Author(s)
      鈴木大慈
    • Organizer
      情報論的学習理論ワークショップ(IBIS2015)
    • Place of Presentation
      エポカルつくば,日本
    • Year and Date
      2015-11-28
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Stochastic Optimization2015

    • Author(s)
      Taiji Suzuki
    • Organizer
      Machine Learning Summer School 2015
    • Place of Presentation
      Kyoto, Japan
    • Year and Date
      2015-09-02
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 多変量線形回帰における一般化リッジ推定量に基づいたモデル選択規準2015

    • Author(s)
      森裕一,鈴木大慈
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      岡山大学
    • Year and Date
      2015-09-06
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Time-Series Analysis on Multiperiodic Conditional Correlation by Sparse Covariance Selection and Its Computational Method2015

    • Author(s)
      リー・マイケル,鈴木大慈
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      岡山大学
    • Year and Date
      2015-09-06
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Gaussian process methods for high dimensional learning2015

    • Author(s)
      Taiji Suzuki
    • Organizer
      統計関連学会連合大会,CSA-KSS-JSS joint international session II: Machine Learning and Its Applications
    • Place of Presentation
      Okayama, Japan
    • Year and Date
      2015-09-08
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 構造的正則化学習における確率的交互方向乗数法2015

    • Author(s)
      鈴木大慈
    • Organizer
      大規模統計モデリングと計算統計
    • Place of Presentation
      東京大学
    • Year and Date
      2015-02-06
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Stochastic Alternating Direction Method of Multipliers and its Recent Development2015

    • Author(s)
      鈴木大慈
    • Organizer
      大規模統計モデリングと計算統計II
    • Place of Presentation
      東京大学大学院数理科学研究科
    • Year and Date
      2015-09-25
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 低ランクテンソル推定におけるベイズ推定量の性質2015

    • Author(s)
      鈴木大慈
    • Organizer
      第9回日本統計学会春季集会
    • Place of Presentation
      明治大学中野キャンパス
    • Year and Date
      2015-03-08
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Bayes Method for Low Rank Tensor Estimation2015

    • Author(s)
      Suzuki, T., Kanagawa, H.
    • Organizer
      International Meeting on “High-Dimensional Data Driven Science”
    • Place of Presentation
      メルパルク京都(京都府京都市)
    • Year and Date
      2015-12-17
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-15H01678
  • [Presentation] Stochastic Alternating Direction Method of Multipliers for Structured Sparsity2015

    • Author(s)
      Taiji Suzuki
    • Organizer
      Workshop on Complex systems Modeling and Estimation Challenges in big data(CSM2015).
    • Place of Presentation
      Tachikawa, Tokyo, Japan
    • Year and Date
      2015-07-13
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Bayes method for low rank tensor estimation2015

    • Author(s)
      Taiji Suzuki and Heishiro Kanagawa
    • Organizer
      International Meeting on “High-Dimensional Data Driven Science” (HD3-2015)
    • Place of Presentation
      Mielparque Kyoto, Japan
    • Year and Date
      2015-12-14
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 確率的最適化から始める機械学習入門2015

    • Author(s)
      鈴木大慈
    • Organizer
      IBIS2015チュートリアル
    • Place of Presentation
      つくば
    • Year and Date
      2015-11-28
    • Invited
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] 非線形テンソル学習手法の高速化とYahoo!ショッピング購買金額予測への適用2015

    • Author(s)
      金川平志郎,清水伸幸,小林隼人,田頭幸浩,鈴木大慈
    • Organizer
      情報論的学習理論ワークショップ(IBIS2015)
    • Place of Presentation
      エポカルつくば
    • Year and Date
      2015-11-27
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 正則化経験誤差最小化問題に対する確率的分散縮小双対平均化法2015

    • Author(s)
      村田智也,鈴木大慈
    • Organizer
      情報論的学習理論ワークショップ(IBIS2015)
    • Place of Presentation
      エポカルつくば
    • Year and Date
      2015-11-27
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Gaussian process methods for high dimensional learning2015

    • Author(s)
      鈴木大慈
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      岡山大学
    • Year and Date
      2015-09-06
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] 確率的最適化から始める機械学習入門2015

    • Author(s)
      鈴木大慈
    • Organizer
      第18回情報論的学習理論ワークショップ チュートリアル
    • Place of Presentation
      つくば国際会議場(茨城県つくば市)
    • Year and Date
      2015-11-28
    • Invited
    • Data Source
      KAKENHI-PROJECT-15H01678
  • [Presentation] Gaussian process methods for high dimensional learning2015

    • Author(s)
      鈴木大慈
    • Organizer
      2015年度統計関連学会連合大会
    • Place of Presentation
      岡山大学(岡山県岡山市)
    • Year and Date
      2015-09-08
    • Data Source
      KAKENHI-PROJECT-15H01678
  • [Presentation] Statistical properties of high dimensional low rank tensor estimators2015

    • Author(s)
      鈴木大慈
    • Organizer
      早稲田大学理工学研究所プロジェクト研究「金融数理および年金数理研究」セミナー
    • Place of Presentation
      早稲田大学
    • Year and Date
      2015-12-22
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] マルチプルカーネル学習とスパース推定の統計的性質2014

    • Author(s)
      鈴木大慈
    • Organizer
      日本数学会年会
    • Place of Presentation
      東京
    • Invited
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] 正定値カーネルを用いた条件付き確率密度推定2014

    • Author(s)
      金川元信,鈴木大慈,福水健次
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      東京
    • Year and Date
      2014-09-14
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] PAC-Bayesian Bound for Gaussian Process Regression and Multiple Kernel Additive Model2014

    • Author(s)
      Taiji Suzuki
    • Organizer
      超高次元データ解析の数理基盤
    • Place of Presentation
      統計数理研究所
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] マルチプルカーネル学習とスパース推定の統計的性質2014

    • Author(s)
      鈴木大慈
    • Organizer
      日本数学会年会
    • Place of Presentation
      学習院大学
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Stochastic Dual Coordinate Ascent with Alternating Direction Method of Multipliers2014

    • Author(s)
      Taiji Suzuki
    • Organizer
      International Conference on Machine Learning (ICML2014)
    • Place of Presentation
      Beijing, China
    • Year and Date
      2014-06-28
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Risk bounds for convex and Bayesian tensor estimators2014

    • Author(s)
      Taiji Suzuki
    • Organizer
      Asymptotic Statistics and Computations 2014 (ASC2014)
    • Place of Presentation
      東京大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] マルチプルカーネル学習およびガウス過程事前分布を用いたスパース加法モデル推定2013

    • Author(s)
      鈴木 大慈
    • Organizer
      高次元データ解析の理論と方法論、及び、関連分野への応用
    • Place of Presentation
      筑波大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Dual Averaging and Proximal Gradient Descent for Online Alternating Direction Multiplier Method2013

    • Author(s)
      Taiji Suzuki
    • Organizer
      The Sixth Workshop on Information Theoretic Methods in Science and Engineering (WITMSE2013)
    • Place of Presentation
      東京大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Dual Averaging and Proximal Gradient Descent for Online Alternating Direction Multiplier Method2013

    • Author(s)
      Suzuki, T.
    • Organizer
      The Sixth Workshop on Information Theoretic Methods in Science and Engineering (WITMSE2013).
    • Place of Presentation
      東京
    • Invited
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] Stochastic Dual Coordinate Ascent with Alternating Direction Method of Multipliers2013

    • Author(s)
      Taiji Suzuki
    • Organizer
      OPT2013: Optimization for Machine Learning, NIPS workshop
    • Place of Presentation
      Lake Tahoe,USA
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 機械学習におけるオンライン確率的最適化の理論2013

    • Author(s)
      鈴木大慈
    • Organizer
      情報処理学会連続セミナー2013,ビッグデータの深化と真価,第一回「ビッグデータ活用のための機械学習技術」
    • Place of Presentation
      東京都,化学会館
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Stochastic Dual Coordinate Ascent with Alternating Direction Method of Multipliers.2013

    • Author(s)
      Suzuki, T.
    • Organizer
      OPT2013, NIPS workshop "Optimization for Machine Learning
    • Place of Presentation
      Lake Tahoe, USA
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] スパース推定における確率集中不等式2013

    • Author(s)
      鈴木 大慈
    • Organizer
      高次元量子トモグラフィにおける統計理論的なアプローチ
    • Place of Presentation
      京都大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Convex Tensor Decomposition via Structured Schatten Norm Regularization2013

    • Author(s)
      Ryota Tomioka and Taiji Suzuki
    • Organizer
      Advances in Neural Information Processing Systems (NIPS2013)
    • Place of Presentation
      Lake Tahoe,USA
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Dual Averaging and Proximal Gradient Descent for Online Alternating Direction Multiplier Method2013

    • Author(s)
      Taiji Suzuki
    • Organizer
      International Conference on Machine Learning (ICML2013)
    • Place of Presentation
      Atlanta, USA
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 低ランク行列推定におけるベイズ推定法の性質2013

    • Author(s)
      鈴木 大慈
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      大阪大学
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] 2値判別における損失関数と不確実性集合の共役性2012

    • Author(s)
      金森 敬文,武田 朗子 ,鈴木 大慈
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      北海道大学
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Fast Learning Rate of Multiple Kernel Learning: Trade-off between Sparsity and Smoothness2012

    • Author(s)
      Taiji Suzuki and Masashi Sugiyama
    • Organizer
      Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS2012)
    • Place of Presentation
      La Palma, Canary Islands
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Fast Learning Rate of Multiple Kernel Learning2012

    • Author(s)
      Taiji Suzuki and Masashi Sugiyama
    • Organizer
      Trade-off between Sparsity and Smoothness. Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS2012)
    • Place of Presentation
      La Palma, Canary Islands
    • Year and Date
      2012-04-21
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] 統計的学習理論チュートリア ル2012

    • Author(s)
      鈴木大慈
    • Organizer
      第15回情報論的学 習理論ワークショップ (IBIS2012)
    • Place of Presentation
      筑波大学東京キャンパス文京校舎
    • Year and Date
      2012-11-07
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] 統計的学習理論チュートリアル:基礎から応用まで2012

    • Author(s)
      鈴木 大慈
    • Organizer
      第15回情報論的学習理論ワークショップ (IBIS2012)
    • Place of Presentation
      筑波大学東京キャンパス文京校舎
    • Invited
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] PAC-Bayesian Bound for Gaussian Process Regression and Multiple Kernel Additive Model2012

    • Author(s)
      Taiji Suzuki
    • Organizer
      Conference on Learning Theory (COLT2012)
    • Place of Presentation
      Edinburgh, Scotland
    • Year and Date
      2012-06-25
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Density-Difference Estimation2012

    • Author(s)
      Masashi Sugiyama, Takafumi Kanamori, Taiji Suzuki, Marthinus Christoffel du Plessis, Song Liu, and Ichiro Takeuchi
    • Organizer
      Advances in Neural Information Processing Systems (NIPS2012)
    • Place of Presentation
      Lake Tahoe, Nevada, United States
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Some convergence results on multiple kernel additive models2012

    • Author(s)
      Taiji Suzuki
    • Organizer
      Nonparametric and High-dimensional Statistics
    • Place of Presentation
      Luminy, France
    • Invited
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] A Conjugate Property between Loss Functions and Uncertainty Sets in Classification Problems2012

    • Author(s)
      Takafumi Kanamori, Akiko Takeda and Taiji Suzuki
    • Organizer
      Conference on Learning Theory (COLT2012)
    • Place of Presentation
      Edinburgh, Scotland
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Some convergence results on multiple kernel additive models.N2012

    • Author(s)
      Taiji Suzuki
    • Organizer
      onparametric and High-dimensionalStatistics
    • Place of Presentation
      Luminy, France
    • Year and Date
      2012-12-18
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] ガウシアンプロセス回帰を用いた加法モデル推定のPAC-Bayesバウンド2012

    • Author(s)
      鈴木 大慈
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      北海道大学
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Relative Density-Ratio Estimation for Robust Distribution Comparison2011

    • Author(s)
      Makoto Yamada, Taiji Suzuki, Takafumi Kanamori, Hirotaka Hachiya and Masashi Sugiyama
    • Organizer
      Advances in Neural Information Processing Systems 24 (NIPS2011)
    • Place of Presentation
      Granada, Spain
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Statistical Performance of Convex Tensor Decomposition2011

    • Author(s)
      Ryota Tomioka, Taiji Suzuki, Kohei Hayashi and Hisashi Kashima
    • Organizer
      Advances in Neural Information Processing Systems 24 (NIPS2011)
    • Place of Presentation
      Granada, Spain
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Fast Convergence Rate of Multiple Kernel Learning with Elastic-net Regularization2011

    • Author(s)
      鈴木大慈, 冨岡亮太, 杉山将
    • Organizer
      第4回IBISML研究会
    • Place of Presentation
      阪大中之島センター
    • Year and Date
      2011-03-29
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] カーネル密度比推定の統計的解析2011

    • Author(s)
      金森敬文, 鈴木大慈, 杉山将
    • Organizer
      第4回IBISML研究会
    • Place of Presentation
      阪大中之島センター
    • Year and Date
      2011-03-29
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] 疎でないマルチプルカーネル学習の速い収束レートおよび最適な正則化に関して2011

    • Author(s)
      鈴木 大慈
    • Organizer
      第14回情報論的学習理論ワークショップ (IBIS2011)
    • Place of Presentation
      奈良女子大学
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Unifying Framework for Fast Learning Rate of Non-Sparse Multiple Kernel Learning2011

    • Author(s)
      Taiji Suzuki
    • Organizer
      Advances in Neural Information Processing Systems 24 (NIPS2011)
    • Place of Presentation
      Granada, Spain.
    • Year and Date
      2011-12-12
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Multiple Kernel Learningの効率的計算法と統計的性質について2011

    • Author(s)
      鈴木 大慈
    • Organizer
      応用数理学会若手の会単独研究会
    • Place of Presentation
      早稲田大学
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Unifying Framework for Fast Learning Rate of Non-Sparse Multiple Kernel Learning2011

    • Author(s)
      Taiji Suzuki
    • Organizer
      Advances in Neural Information Processing Systems 24 (NIPS2011)
    • Place of Presentation
      Granada, Spain
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] スパース正則化学習の学習性能,特にスパース性と汎化誤差の関係について2010

    • Author(s)
      鈴木大慈
    • Organizer
      第13回情報論的学習理論ワークショップ(IBIS2010)
    • Place of Presentation
      東京大学
    • Year and Date
      2010-11-04
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Conditional density estimation via least-squares density ratio estimation2010

    • Author(s)
      Masashi Sugiyama, Ichiro Takeuchi, Takafumi Kanamori, Taiji Suzuki, Hirotaka Hachiya, Daisuke Okanohara
    • Organizer
      Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS2010)
    • Place of Presentation
      Chia Laguna Resort, Sardinia, Italy
    • Year and Date
      2010-05-14
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] An Efficient and General Augmented Lagrangian Algorithm for Learning Low-Rank Matrices2010

    • Author(s)
      Ryota Tomioka, Taiji Suzuki, Masashi Sugiyama, Hisashi Kashima
    • Organizer
      27th International Conference on Machine Learning International (ICML2010)
    • Place of Presentation
      Haifa, Israel
    • Year and Date
      2010-06-22
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Sufficient dimension reduction via squared-loss mutual information estimation2010

    • Author(s)
      Taiji Suzuki, Masashi Sugiyama
    • Organizer
      Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS2010)
    • Place of Presentation
      Chia Laguna Resort, Sardinia, Italy
    • Year and Date
      2010-05-13
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Direct density ratio estimation with dimensionality reduction2010

    • Author(s)
      Masashi Sugiyama, Satoshi Hara, Paul von Bunau, Taiji Suzuki, Takafumi Kanamori, Motoaki Kawanabe
    • Organizer
      2010 SIAM International Conference on Data Mining (SDM2010)
    • Place of Presentation
      Columbus, Ohio, USA
    • Year and Date
      2010-04-30
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] 密度比の推定による2標本検定2010

    • Author(s)
      金森敬文, 鈴木大慈, 杉山将
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      早稲田大学
    • Year and Date
      2010-09-06
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] A computational method to predict PSA evolution for androgen deprivation therapy2010

    • Author(s)
      Taiji Suzuki, Nicholas Bruchovsky, Kazuyuki Aihara
    • Organizer
      Sixth International Symposium on Hormonal Oncogenesis
    • Place of Presentation
      Sheraton Grande Tokyo Bay Hotel, Tokyo
    • Year and Date
      2010-09-14
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Elasticnet型正則化を用いたMultiple Kernel Learningの漸近的性質について2010

    • Author(s)
      鈴木大慈, 冨岡亮太, 杉山将
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      早稲田大学
    • Year and Date
      2010-09-06
    • Data Source
      KAKENHI-PROJECT-22700289
  • [Presentation] Risk Bounds of Convex and Bayes Tensor Estimators: Near Optimal Rate without Strong Convexity

    • Author(s)
      Taiji Suzuki
    • Organizer
      International Workshop on Spatial and Temporal Modeling from Statistical, Machine Learning and Engineering perspectives (STM2014)
    • Place of Presentation
      Tokyo Japan
    • Year and Date
      2014-06-28 – 2014-06-29
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Stochastic Dual Coordinate Ascent with ADMM

    • Author(s)
      Taiji Suzuki
    • Organizer
      SIAM Conference on Optimization (SIAM-OPT2014)
    • Place of Presentation
      San Diego, USA
    • Year and Date
      2014-05-19 – 2014-05-22
    • Invited
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] スパース推定概観:モデル・理論・応用

    • Author(s)
      鈴木大慈
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      東京
    • Year and Date
      2014-09-13 – 2014-09-16
    • Invited
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Presentation] スパース推定概観:モデル・理論・応用

    • Author(s)
      鈴木大慈
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      東京大学
    • Year and Date
      2014-09-13 – 2014-09-16
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Risk Bounds of Convex and Bayes Tensor Estimators: Near Optimal Rate without Strong Convexity

    • Author(s)
      Taiji Suzuki
    • Organizer
      International Workshop on Spatial and Temporal Modeling from Statistical, Machine Learning and Engineering perspectives (STM2014)
    • Place of Presentation
      Tokyo
    • Year and Date
      2014-07-28 – 2014-07-29
    • Invited
    • Data Source
      KAKENHI-PLANNED-25120012
  • [Presentation] 正定値カーネルを用いた条件付き確率密度推定

    • Author(s)
      金川元信,鈴木 大慈,福水健次
    • Organizer
      統計関連学会連合大会
    • Place of Presentation
      東京大学
    • Year and Date
      2014-09-13 – 2014-09-16
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Stochastic Dual Coordinate Ascent with ADMM

    • Author(s)
      Taiji Suzuki
    • Organizer
      SIAM Conference on Optimization (SIAM-OPT2014)
    • Place of Presentation
      San Diego, USA
    • Year and Date
      2014-05-19 – 2014-05-22
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Presentation] Risk Bounds of Convex and Bayes Tensor Estimators: Near Optimal Rate without Strong Convexity

    • Author(s)
      Taiji Suzuki
    • Organizer
      International Workshop on Spatial and Temporal Modeling from Statistical, Machine Learning and Engineering perspectives (STM2014)
    • Place of Presentation
      東京
    • Year and Date
      2014-07-28 – 2014-07-29
    • Invited
    • Data Source
      KAKENHI-PROJECT-26280009
  • [Presentation] A Consistent Method for Graph Based Anomaly Localization

    • Author(s)
      Satoshi Hara, Tetsuro Morimura, Toshihiro Takahashi, Hiroki Yanagisawa, Taiji Suzuki
    • Organizer
      The 18th International Conference on Artificial Intelligence and Statistics (AISTATS2015)
    • Place of Presentation
      San Diego, USA
    • Year and Date
      2015-05-09 – 2015-05-12
    • Data Source
      KAKENHI-PROJECT-25730013
  • [Presentation] Support Consistency of Direct Sparse-Change Learning in Markov Networks

    • Author(s)
      Song Liu, Taiji Suzuki, and Masashi Sugiyama
    • Organizer
      The Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI2015)
    • Place of Presentation
      Austin Texas, USA
    • Year and Date
      2015-01-25 – 2015-01-30
    • Data Source
      KAKENHI-PROJECT-25730013
  • 1.  Fukumizu Kenji (60311362)
    # of Collaborated Projects: 3 results
    # of Collaborated Products: 11 results
  • 2.  NISHIYAMA Yu (60586395)
    # of Collaborated Projects: 2 results
    # of Collaborated Products: 0 results
  • 3.  AOSHIMA Makoto (90246679)
    # of Collaborated Projects: 2 results
    # of Collaborated Products: 0 results
  • 4.  金森 敬文 (60334546)
    # of Collaborated Projects: 2 results
    # of Collaborated Products: 1 results
  • 5.  蛭川 潤一 (10386617)
    # of Collaborated Projects: 2 results
    # of Collaborated Products: 0 results
  • 6.  矢田 和善 (90585803)
    # of Collaborated Projects: 2 results
    # of Collaborated Products: 0 results
  • 7.  星野 伸明 (00313627)
    # of Collaborated Projects: 2 results
    # of Collaborated Products: 0 results
  • 8.  小森 理 (60586379)
    # of Collaborated Projects: 2 results
    # of Collaborated Products: 0 results
  • 9.  松井 秀俊 (90633305)
    # of Collaborated Projects: 2 results
    # of Collaborated Products: 0 results
  • 10.  植木 優夫 (10515860)
    # of Collaborated Projects: 2 results
    # of Collaborated Products: 0 results
  • 11.  LIU Song (80760579)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 9 results
  • 12.  AIHARA Kazuyuki (40167218)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 13.  冨岡 亮太 (70518282)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 2 results
  • 14.  小林 景 (90465922)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 2 results
  • 15.  宮野 悟 (50128104)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 16.  奥 牧人 (30633565)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 2 results
  • 17.  藤原 寛太郎 (00557704)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 18.  中岡 慎治 (30512040)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 19.  森野 佳生 (90712737)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 20.  梶田 真司 (40804191)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 21.  今泉 允聡 (90814088)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 22.  宇野 力 (20282155)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 23.  廣瀬 慧 (40609806)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 24.  柳原 宏和 (70342615)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 25.  竹之内 高志 (50403340)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 26.  井元 清哉 (10345027)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 27.  塩濱 敬之 (40361844)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 28.  石井 晶 (20801161)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 29.  江頭 健斗 (20979869)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 30.  荒木 由布子 (80403913)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 31.  川野 秀一 (50611448)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 32.  松田 安昌 (10301590)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 33.  田畑 耕治 (30453814)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 34.  片山 翔太 (50742459)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 35.  中山 優吾 (40884169)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 36.  杉山 将
    # of Collaborated Projects: 0 results
    # of Collaborated Products: 1 results
  • 37.  岡田 眞里子
    # of Collaborated Projects: 0 results
    # of Collaborated Products: 1 results
  • 38.  二反田 篤史
    # of Collaborated Projects: 0 results
    # of Collaborated Products: 1 results
  • 39.  小松 英彦
    # of Collaborated Projects: 0 results
    # of Collaborated Products: 1 results

URL: 

Are you sure that you want to link your ORCID iD to your KAKEN Researcher profile?
* This action can be performed only by the researcher himself/herself who is listed on the KAKEN Researcher’s page. Are you sure that this KAKEN Researcher’s page is your page?

この研究者とORCID iDの連携を行いますか?
※ この処理は、研究者本人だけが実行できます。

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi