Nitanda Atsushi

Affiliation and department：
Job title： Principal Scientist
Homepage URL (1)： https://sites.google.com/site/atsushinitanda

Research field (1)： Mathematical informatics

Research keywords (3)： Deep Learning , Stochastic Optimization , Machine Learning

Research theme for competitive and other funds (3)：

2022 - 2026 Development of adaptive leanring method based on optimization of probability measures
2019 - 2023 深層学習の潜在的正則構造の理解に基づく学習法の安定化と高速化
2019 - 2021 超高次元機械学習モデルの学習ダイナミクスの究明と効率的学習法の開発

Papers (25)：

Kazusato Oko, Taiji Suzuki, Atsushi Nitanda, Denny Wu. Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization. International Conference on Learning Representations. 2022
Atsushi Nitanda, Denny Wu, Taiji Suzuki. Convex Analysis of the Mean Field Langevin Dynamics. International Conference on Artificial Intelligence and Statistics. 2022
Atsushi Suzuki, Atsushi Nitanda, Jing Wang, Linchuan Xu, Kenji Yamanishi, Marc Cavazza. Generalization Bounds for Graph Embedding Using Negative Sampling: Linear vs Hyperbolic. Neural Information Processing Systems. 2021
Atsushi Nitanda, Denny Wu, Taiji Suzuki. Particle Dual Averaging: Optimization of Mean Field Neural Networks with Global Convergence Rate Analysis. Neural Information Processing Systems. 2021
Taiji Suzuki, Atsushi Nitanda. Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space. Neural Information Processing Systems. 2021

ｍore...

MISC (9)：

ｍore...

Patents (1)：

Books (1)：

Lectures and oral presentations (49)：

Convex Analysis of the Mean Field Langevin Dynamics
(Workshop on Functional Inference and Machine Intelligence 2022)
Efficient optimization methods for two-layer neural networks in mean-field regime
(CREST-Deep meeting 2021)
平均場ニューラルネットワークの効率的最適化
(AI数理セミナー 2021)
Particle Stochastic Dual Coordinate Ascent: Exponential Convergent Algorithm for Mean Field Neural Network Optimization
(情報論的学習理論ワークショップ 2021)
平均場ニューラルネットワークの効率的最適化法
(統計関連学会連合大会 2021)

ｍore...

Education (2)：

2017 - 2018 The University of Tokyo The Graduate School of Information Science and Technology Department of Mathematical Informatics
2007 - 2009 The University of Tokyo

Professional career (1)：

Work history (8)：

2024/01 - 現在 A*STAR
2021/04 - 2023/12 Kyushu Institute of Technology Faculty of Computer Science and Systems Engineering Associate Professor
2018/12 - 2023/12 RIKEN AIP Visiting Researcher
2019/10 - 2023/03 JST PRESTO Researcher
2018/10 - 2021/03 The University of Tokyo The Graduate School of Information Science and Technology

Show all

Awards (5)：

2021/04 - The Ninth International Conference on Learning Representations Outstanding Paper Award Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime
2019/11 - IEEE International Conference on Data Mining ICDM '19 Best Paper Candidate for KAIS Publication Sharp Characterization of Optimal Minibatch Size for Stochastic Finite Sum Convex Optimization
2019/11 - 第22回情報論的学習理論ワークショップ(IBIS2019) ベストプレゼンテーション賞 SGDの挙動解析に基づくデータクレンジング
2019/03 - Graduate School of Information Science and Technology, The University of Tokyo Dean's Award
2009/03 - Graduate School of Mathematical Sciences, The University of Tokyo Dean's Award

※ Researcher’s information displayed in J-GLOBAL is based on the information registered in researchmap. For details, see here.

Return to Previous Page