Kazusato Oko

5

Papers

25

Total Citations

Papers (5)

Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems

Flow matching achieves almost minimax optimal convergence

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

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

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