Tomoya Murata

3

Papers

0

Total Citations

Papers (3)

Simple Minimax Optimal Byzantine Robust Algorithm for Nonconvex Objectives with Uniform Gradient Heterogeneity

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

Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning

NeurIPS 2022arXiv