• A
  • A
  • A
日本語 Help
Science and technology information site for articles, patents, researchers information, etc.
Rchr
J-GLOBAL ID:202201020172103385   Update date: Mar. 05, 2025

Takahashi Takashi

タカハシ タカシ | Takahashi Takashi
Affiliation and department:
Job title: Assistant professor
Research field  (2): Soft computing ,  Statistical science
Research keywords  (3): Statistical Mechanics ,  Mathematical Statistics ,  Statistical Learning Theory
Research theme for competitive and other funds  (5):
  • 2024 - 2027 Development of variational methods for the explanation and understanding of learning systems
  • 2023 - 2027 Constructing a mathematical foundation for heuristics based on transfer learning
  • 2022 - 2027 Statistical mechanics approach to high-dimensional machine learning
  • 2021 - 2023 Statistical mechanics of heuristic methods in multi-stage learning
  • 2019 - 2021 A statistical mechanics approach to reliability assessment in large scale statistical inference
Papers (11):
  • Takashi Takahashi. Replica Analysis for Ensemble Techniques in Variable Selection. Journal of the Physical Society of Japan. 2024. 94. 3. 031011-1-031011-10
  • Takashi Takahashi. A replica analysis of under-bagging. Transactions on Machine Learning Research. 2024
  • Siqi Na, Tianyao Huang, Yimin Liu, Takashi Takahashi, Yoshiyuki Kabashima, Xiqin Wang. Compressed sensing radar detectors under the row-orthogonal design model: a statistical mechanics perspective. IEEE Transactions on Signal Processing. 2023. 1-16
  • Takashi Takahashi. Role of Bootstrap Averaging in Generalized Approximate Message Passing. 2023 IEEE International Symposium on Information Theory (ISIT). 2023
  • Koki Okajima, Xiangming Meng, Takashi Takahashi, Yoshiyuki Kabashima. Average case analysis of Lasso under ultra-sparse conditions. Proceedings of The 26th International Conference on Artificial Intelligence and Statistics. 2023. 206. 11317-11330
more...
Lectures and oral presentations  (53):
  • Dynamical Mean Field Theory for Alternating Minimization in Bilinear Regression
    (Towards a theory for typical-case algorithmic hardness 2025)
  • 機械学習のための統計学入門
    (物理屋のための機械学習講義 2025)
  • A replica analysis of under-bagging
    (DAIKIN International Symposium on Physics of Intelligence 2024)
  • アンダーバギング法の比例的漸近論
    (第27回情報論的学習理論ワークショップ 2024)
  • 自己蒸留におけるソフトラベルの役割
    (第27回情報論的学習理論ワークショップ 2024)
more...
Education (5):
  • 2017 - 2020 Tokyo Institute of Technology, School of Computing Department of Mathematical and Computing Science
  • 2013 - 2015 The University of Tokyo Graduate School of Arts and Sciences Department of Basic Science
  • 2011 - 2013 The University of Tokyo College of Arts and Sciences Department of Basic Science
  • 2010 - 2011 The University of Tokyo The Faculty of Engineering Department of Applied Physics
  • 2008 - 2010 The University of Tokyo College of Arts and Sciences
Professional career (1):
  • Doctor of Science (Tokyo Institute of Technology (Supervisor: Yoshiyuki Kabashima))
Work history (5):
  • 2020/11 - 現在 The University of Tokyo Institute for Physics of Intelligence Assistant Professor
  • 2020/10 - 2020/11 Institute for Physics of Intelligence, The University of Tokyo postDoc
  • 2019/04 - 2020/09 Tokyo Institute of Technology Department of Mathematical and Computing Science JSPS Research Fellow (DC2)
  • 2018/08 - 2019/03 TOYOTA InfoTechnology Center
  • 2015/04 - 2017/03 Kozo Keikaku Engineering Inc. Innovative Information Technology Department
Committee career (1):
  • 2022/10 - 2023/09 The Physical Society of Japan Devision 11, Steering Committee
Awards (2):
  • 2025/03 - IOP (Institute of Physics) IOP Trusted Reviewer status
  • 2015/03 - Graduate School of Arts and Sciences, The University of Tokyo, Komaba Outstanding Graduate Student Award
Association Membership(s) (2):
THE JAPAN STATISTICAL SOCIETY ,  THE PHYSICAL SOCIETY OF JAPAN
※ Researcher’s information displayed in J-GLOBAL is based on the information registered in researchmap. For details, see here.

Return to Previous Page