Kazusato Oko

According to our database, Kazusato Oko authored at least 16 papers between 2022 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Pretrained transformer efficiently learns low-dimensional target functions in-context.

Kazusato Oko, Yujin Song, Taiji Suzuki, Denny Wu

CoRR, 2024

Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit.

Jason D. Lee, Kazusato Oko, Taiji Suzuki, Denny Wu

CoRR, 2024

Flow matching achieves minimax optimal convergence.

Kenji Fukumizu, Taiji Suzuki, Noboru Isobe, Kazusato Oko, Masanori Koyama

CoRR, 2024

Mean Field Langevin Actor-Critic: Faster Convergence and Global Optimality beyond Lazy Learning.

Kakei Yamamoto, Kazusato Oko, Zhuoran Yang, Taiji Suzuki

Proceedings of the Forty-first International Conference on Machine Learning, 2024

SILVER: Single-loop variance reduction and application to federated learning.

Kazusato Oko, Shunta Akiyama, Denny Wu, Tomoya Murata, Taiji Suzuki

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data.

Atsushi Nitanda, Kazusato Oko, Taiji Suzuki, Denny Wu

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems.

Juno Kim, Kakei Yamamoto, Kazusato Oko, Zhuoran Yang, Taiji Suzuki

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations.

Kazusato Oko, Yujin Song, Taiji Suzuki, Denny Wu

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

2023

Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond.

Taiji Suzuki, Denny Wu, Kazusato Oko, Atsushi Nitanda

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Diffusion Models are Minimax Optimal Distribution Estimators.

Kazusato Oko, Shunta Akiyama, Taiji Suzuki

Proceedings of the International Conference on Machine Learning, 2023

Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems.

Atsushi Nitanda, Kazusato Oko, Denny Wu, Nobuhito Takenouchi, Taiji Suzuki

Proceedings of the International Conference on Machine Learning, 2023

Nearly Tight Spectral Sparsification of Directed Hypergraphs.

Kazusato Oko, Shinsaku Sakaue, Shin-ichi Tanigawa

Proceedings of the 50th International Colloquium on Automata, Languages, and Programming, 2023

2022

Versatile Single-Loop Method for Gradient Estimator: First and Second Order Optimality, and its Application to Federated Learning.

Kazusato Oko, Shunta Akiyama, Tomoya Murata, Taiji Suzuki

CoRR, 2022

Nearly Tight Spectral Sparsification of Directed Hypergraphs by a Simple Iterative Sampling Algorithm.

Kazusato Oko, Shinsaku Sakaue, Shin-ichi Tanigawa

CoRR, 2022

MOCHA: mobile check-in application for university campuses beyond COVID-19.

Yuuki Nishiyama, Hiroaki Murakami, Ryoto Suzuki, Kazusato Oko, Issey Sukeda, Kaoru Sezaki, Yoshihiro Kawahara

Proceedings of the MobiHoc '22: The Twenty-third International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing, Seoul, Republic of Korea, October 17, 2022

Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization.

Kazusato Oko, Taiji Suzuki, Atsushi Nitanda, Denny Wu

Proceedings of the Tenth International Conference on Learning Representations, 2022