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

Takahashi Takashi  高橋 昂

ORCIDConnect your ORCID iD *help
Researcher Number 90906661
Other IDs
Affiliation (Current) 2025: 東京大学, 大学院理学系研究科(理学部), 助教
Affiliation (based on the past Project Information) *help 2021 – 2023: 東京大学, 大学院理学系研究科(理学部), 助教
Review Section/Research Field
Principal Investigator
Basic Section 61040:Soft computing-related / 1002:Human informatics, applied informatics and related fields
Keywords
Principal Investigator
機械学習 / レプリカ法 / 半教師あり学習 / 統計力学 / 統計物理学 / 転移学習 / 不均衡データ / モデル圧縮 / 近似確率伝搬法 / アンサンブル学習 / 疑似ラベル / 自己学習
  • Research Projects

    (2 results)
  • Research Products

    (9 results)
  •  Constructing a mathematical foundation for heuristics based on transfer learningPrincipal Investigator

    • Principal Investigator
      高橋 昂
    • Project Period (FY)
      2023 – 2026
    • Research Category
      Grant-in-Aid for Early-Career Scientists
    • Review Section
      Basic Section 61040:Soft computing-related
    • Research Institution
      The University of Tokyo
  •  Statistical mechanics of heuristic methods in multi-stage learningPrincipal Investigator

    • Principal Investigator
      Takahashi Takashi
    • Project Period (FY)
      2021 – 2023
    • Research Category
      Grant-in-Aid for Research Activity Start-up
    • Review Section
      1002:Human informatics, applied informatics and related fields
    • Research Institution
      The University of Tokyo

All 2023 2022

All Journal Article Presentation

  • [Journal Article] Average case analysis of Lasso under ultra sparse conditions2023

    • Author(s)
      Koki Okajima, Xiangming Meng, Takashi Takahashi, Yoshiyuki Kabashima
    • Journal Title

      Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR

      Volume: 206 Pages: 11317-11330

    • Peer Reviewed / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-21K21310
  • [Journal Article] Role of Bootstrap Averaging in Generalized Approximate Message Passing2023

    • Author(s)
      Takahashi Takashi
    • Journal Title

      IEEE International Symposium on Information Theory (ISIT)

      Volume: 2023 Pages: 767-772

    • DOI

      10.1109/isit54713.2023.10206490

    • Peer Reviewed / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-23K16960, KAKENHI-PROJECT-21K21310
  • [Journal Article] Compressed Sensing Radar Detectors Under the Row-Orthogonal Design Model: A Statistical Mechanics Perspective2023

    • Author(s)
      Na Siqi、Huang Tianyao、Liu Yimin、Takahashi Takashi、Kabashima Yoshiyuki、Wang Xiqin
    • Journal Title

      IEEE Transactions on Signal Processing

      Volume: 71 Pages: 2668-2682

    • DOI

      10.1109/tsp.2023.3297743

    • Peer Reviewed / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-23K16960, KAKENHI-PROJECT-21K21310, KAKENHI-PROJECT-20H00620
  • [Journal Article] Average case analysis of Lasso under ultra sparse conditions2023

    • Author(s)
      Koki Okajima, Xiangming Meng, Takashi Takahashi, Yoshiyuki Kabashima
    • Journal Title

      Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR

      Volume: 206 Pages: 11317-11330

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-23K16960
  • [Presentation] Exploring bagging with structured data: Insights from precise asymptotics2023

    • Author(s)
      Takashi Takahashi
    • Organizer
      Exploring bagging with structured data: Insights from precise asymptotics
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-23K16960
  • [Presentation] A Statistical Mechanics Analysis of Iterative Self-Training2023

    • Author(s)
      Takashi Takahashi
    • Organizer
      STATPHYS28
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-21K21310
  • [Presentation] Exploring bagging with structured data: Insights from precise asymptotics2023

    • Author(s)
      Takashi Takahashi
    • Organizer
      Workshop on Learning and Inference from Structured Data: Universality, Correlations and Beyond | (smr 3850)
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-21K21310
  • [Presentation] A Statistical Mechanics Analysis of Iterative Self-Training2023

    • Author(s)
      Takashi Takahashi
    • Organizer
      STATPHYS28
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-23K16960
  • [Presentation] Sharp Asymptotics of Self-training with Linear Classifier2022

    • Author(s)
      Takashi Takahashi
    • Organizer
      Youth in High-Dimensions: Recent Progress in Machine Learning, High-Dimensional Statistics and Inference
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-21K21310

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