Lee Ching-pei 李静沛

Researcher Number	00984767
Other IDs
Affiliation (Current)	2026: 統計数理研究所, 先端データサイエンス研究系, 准教授
Affiliation (based on the past Project Information) *help	2023 – 2024: 統計数理研究所, 先端データサイエンス研究系, 准教授
Review Section/Research Field	Principal Investigator Basic Section 61030:Intelligent informatics-related / 1001:Information science, computer engineering, and related fields
Keywords	Principal Investigator Adaptive methods / Deep learning / Structured optimization / Federated learning / Nonsmooth optimization / Regularized optimization / regularized optimization / proximal methods / nonlinear optimization / Adaptive proximal method … More / Model condensation / Low-rank structure / model condensation / proximal mehods / structured models / deep learning Less

Research Projects
(2 results)
Research Products
(7 results)

Efficient Federated Learning for Deep Learning Through Structured TrainingPrincipal Investigator
- Principal Investigator
  
  李静沛
- Project Period (FY)
  2024 – 2026
- Research Category
  
  Grant-in-Aid for Early-Career Scientists
- Review Section
  
  Basic Section 61030:Intelligent informatics-related
- Research Institution
  The Institute of Statistical Mathematics
Condensation and Prediction Acceleration for Deep Learning Through Low-rank Regularization and Adaptive Proximal MethodsPrincipal Investigator
- Principal Investigator
  
  Lee Ching-pei
- Project Period (FY)
  2023 – 2024
- Research Category
  
  Grant-in-Aid for Research Activity Start-up
- Review Section
  
  1001:Information science, computer engineering, and related fields
- Research Institution
  The Institute of Statistical Mathematics

All 2025 2024

All Journal Article

[Journal Article] Global Convergence and Acceleration of Projection Methods for Feasibility Problems Involving Union Convex Sets2025
- Author(s)
  Alcantara Jan Harold、Lee Ching-pei
- Journal Title
  
  Journal of Optimization Theory and Applications
  
  Volume: 204 Issue: 2
- DOI
  10.1007/s10957-024-02580-6
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-24K20845
[Journal Article] Accelerating nuclear-norm regularized low-rank matrix optimization through Burer-Monteiro decomposition2024
- Author(s)
  Ching-pei Lee, Ling Liang, Tianyun Tang, Kim-Chuan Toh
- Journal Title
  
  Journal of Machine Learning Research
  
  Volume: 25 Pages: 1-52
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-23K19981
[Journal Article] Accelerated policy gradient: On the convergence rates of the nesterov momentum for reinforcement learning2024
- Author(s)
  Chen, Yen-Ju, Huang, Nai-Chieh, Lee, Ching-pei, and Hsieh, Ping-Chun
- Journal Title
  
  Proceedings of the 41st International Conference on Machine Learning
  
  Volume: -
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-23K19981
[Journal Article] Accelerated Policy Gradient: On the Convergence Rates of the Nesterov Momentum for Reinforcement Learning2024
- Author(s)
  Yen-Ju Chen,Nai-Chieh Huang, Ching-pei Lee, and Ping-Chun Hsieh
- Journal Title
  
  Proceedings of the 41st International Conference on Machine Learning
  
  Volume: -
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-24K20845
[Journal Article] Regularized adaptive momentum dual averaging with an efficient inexact subproblem solver for training structured neural network2024
- Author(s)
  Zih-Syuan Huang, Ching-pei Lee
- Journal Title
  
  Advances in Neural Information Processing Systems
  
  Volume: 37 Pages: 128489-128515
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-24K20845
[Journal Article] Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network2024
- Author(s)
  Zih-Syuan Huang, Ching-pei Lee
- Journal Title
  
  Advances in Neural Information Processing Systems
  
  Volume: 37 Pages: 128489-128515
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-23K19981
[Journal Article] Accelerating nuclear-norm regularized low-rank matrix optimization through Burer-Monteiro decomposition2024
- Author(s)
  Ching-pei Lee, Ling Liang, Tianyun Tang, Kim-Chuan Toh
- Journal Title
  
  Journal of Machine Learning Research
  
  Volume: 25(379) Pages: 1-52
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-24K20845

Lee Ching-pei 李 静沛

Research Projects

Research Products

Efficient Federated Learning for Deep Learning Through Structured TrainingPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Condensation and Prediction Acceleration for Deep Learning Through Low-rank Regularization and Adaptive Proximal MethodsPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

[Journal Article] Global Convergence and Acceleration of Projection Methods for Feasibility Problems Involving Union Convex Sets2025

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Accelerating nuclear-norm regularized low-rank matrix optimization through Burer-Monteiro decomposition2024

Author(s)

Journal Title

Data Source

[Journal Article] Accelerated policy gradient: On the convergence rates of the nesterov momentum for reinforcement learning2024

Author(s)

Journal Title

Data Source

[Journal Article] Accelerated Policy Gradient: On the Convergence Rates of the Nesterov Momentum for Reinforcement Learning2024

Author(s)

Journal Title

Data Source

[Journal Article] Regularized adaptive momentum dual averaging with an efficient inexact subproblem solver for training structured neural network2024

Author(s)

Journal Title

Data Source

[Journal Article] Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network2024

Author(s)

Journal Title

Data Source

[Journal Article] Accelerating nuclear-norm regularized low-rank matrix optimization through Burer-Monteiro decomposition2024

Author(s)

Journal Title

Data Source

Lee Ching-pei 李静沛