Shunta Akiyama

According to our database, Shunta Akiyama authored at least 7 papers between 2021 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

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

2023

Diffusion Models are Minimax Optimal Distribution Estimators.

Kazusato Oko, Shunta Akiyama, Taiji Suzuki

Proceedings of the International Conference on Machine Learning, 2023

Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods.

Shunta Akiyama, Taiji Suzuki

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Optimal design of lottery with cumulative prospect theory.

Shunta Akiyama, Mitsuaki Obara, Yasushi Kawase

CoRR, 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

2021

On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting.

Shunta Akiyama, Taiji Suzuki

Proceedings of the 38th International Conference on Machine Learning, 2021

Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods.

Taiji Suzuki, Shunta Akiyama

Proceedings of the 9th International Conference on Learning Representations, 2021