Scholar
Taiji Suzuki
Google Scholar ID: x8osrBsAAAAJ
The University of Tokyo
Citations & Impact
Citations
6,603
H-index
37
i10-index
111
Publications
20
Co-authors
12
list available
Contact
No contact links provided.
Publications
Cited
0
Resume (English only)
Academic Achievements
- - Naoki Nishikawa, Taiji Suzuki: State Space Models are Provably Comparable to Transformers in Dynamic Token Selection. ICLR 2025.
- - Toshimitsu Uesaka, Taiji Suzuki, Yuhta Takida, Chieh-Hsin Lai, Naoki Murata, Yuki Mitsufuji: Weighted Point Cloud Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric. ICLR 2025.
- - Bingrui Li, Wei Huang, Andi Han, Zhanpeng Zhou, Taiji Suzuki, Jun Zhu, Jianfei Chen: On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent. ICLR 2025.
- - Juno Kim, Taiji Suzuki: Transformers Provably Solve Parity Efficiently with Chain of Thought. ICLR 2025. Oral presentation (1.82% of all submissions; 213/11672).
- - Juno Kim, Dimitri Meunier, Arthur Gretton, Taiji Suzuki, Zhu Li: Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression. ICLR 2025.
- - Kenji Fukumizu, Taiji Suzuki, Noboru Isobe, Kazusato Oko, Masanori Koyama: Flow matching achieves almost minimax optimal convergence. ICLR 2025.
- - Ryotaro Kawata, Kazusato Oko, Atsushi Nitanda, Taiji Suzuki: Direct Distributional Optimization for Provable Alignment of Diffusion Models. ICLR 2025.
- - Wei Huang, Yuan Cao, Haonan Wang, Xin Cao, Taiji Suzuki: Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptrons. AISTATS 2025. accepted.
- - Tomoya Murata, Atsushi Nitanda, Taiji Suzuki: Clustered Involution Equivariant Networks. ICLR 2025.
Research Experience
- - 2006-2009: JSPS Research Fellow (DC1)
- - 2009-2013: Assistant Professor (or Research Associate, with no students) at The University of Tokyo
- - 2013-2017: Associate Professor at Tokyo Institute of Technology
- - 2017-Present: Associate Professor at The University of Tokyo
- - 2014-2018: Sakigake (PRESTO), JST
Education
- - Bachelor of Engineering from Mathematical Engineering Course, Department of Mathematical Engineering and Information Physics, Faculty of Engineering, The University of Tokyo, 2004.
- - Master of Information Science and Technology from Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo, 2006. (supervisor: Professor Kazuyuki Aihara)
- - Ph.D. of Information Science and Technology from Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo, 2009. (thesis advisor: Associate Professor Fumiyasu Komaki)
Background
- Research interests include machine learning and statistics, particularly statistical learning theory, deep learning, kernel methods, nonparametric convergence analysis, optimization, stochastic optimization, optimization for deep learning, information geometry, prior selection, and objective Bayes.
