Murata, Tomoya

12 publications

TMLR 2025 Adaptive Clipping for Differential Private Federated Learning in Interpolation Regimes Takumi Fukami, Tomoya Murata, Kenta Niwa

AISTATS 2025 Clustered Invariant Risk Minimization Tomoya Murata, Atsushi Nitanda, Taiji Suzuki

ICML 2024 SILVER: Single-Loop Variance Reduction and Application to Federated Learning Kazusato Oko, Shunta Akiyama, Denny Wu, Tomoya Murata, Taiji Suzuki

ICLR 2024 Simple Minimax Optimal Byzantine Robust Algorithm for Nonconvex Objectives with Uniform Gradient Heterogeneity Tomoya Murata, Kenta Niwa, Takumi Fukami, Iifan Tyou

ICML 2023 DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning Tomoya Murata, Taiji Suzuki

NeurIPS 2022 Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning Tomoya Murata, Taiji Suzuki

NeurIPSW 2022 Reducing Communication in Nonconvex Federated Learning with a Novel Single-Loop Variance Reduction Method Kazusato Oko, Shunta Akiyama, Tomoya Murata, Taiji Suzuki

AISTATS 2021 Gradient Descent in RKHS with Importance Labeling Tomoya Murata, Taiji Suzuki

ICML 2021 Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning Tomoya Murata, Taiji Suzuki

IJCAI 2020 Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and Its Generalization Error Taiji Suzuki, Hiroshi Abe, Tomoya Murata, Shingo Horiuchi, Kotaro Ito, Tokuma Wachi, So Hirai, Masatoshi Yukishima, Tomoaki Nishimura

NeurIPS 2018 Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation Tomoya Murata, Taiji Suzuki

NeurIPS 2017 Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization Tomoya Murata, Taiji Suzuki