Tomoya Murata

Publication Activity (10 Years)

Years Active: 2014-2024
Publications (10 Years): 22

Top Topics

Risk Minimization

Spectral Analysis

Thresholding Method

Top Venues

Publications

Takumi Fukami, Tomoya Murata, Kenta Niwa, Iifan Tyou
DP-Norm: Differential Privacy Primal-Dual Algorithm for Decentralized Federated Learning. IEEE Trans. Inf. Forensics Secur. 19 (2024)
Tomoya Murata, Kenta Niwa, Takumi Fukami, Iifan Tyou
Simple Minimax Optimal Byzantine Robust Algorithm for Nonconvex Objectives with Uniform Gradient Heterogeneity. ICLR (2024)
Iifan Tyou, Tomoya Murata, Takumi Fukami, Yuki Takezawa, Kenta Niwa
A Localized Primal-Dual Method for Centralized/Decentralized Federated Learning Robust to Data Heterogeneity. IEEE Trans. Signal Inf. Process. over Networks 10 (2024)
Tomoya Murata, Taiji Suzuki
DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning. ICML (2023)
Tomoya Murata, Taiji Suzuki
DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning. CoRR (2023)
Kazusato Oko, Shunta Akiyama, Tomoya Murata, Taiji Suzuki
Versatile Single-Loop Method for Gradient Estimator: First and Second Order Optimality, and its Application to Federated Learning. CoRR (2022)
Tomoya Murata, Taiji Suzuki
Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning. NeurIPS (2022)
Tomoya Murata, Taiji Suzuki
Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning. CoRR (2022)
Tomoya Murata, Taiji Suzuki
Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning. ICML (2021)
Atsushi Nitanda, Tomoya Murata, Taiji Suzuki
Sharp characterization of optimal minibatch size for stochastic finite sum convex optimization. Knowl. Inf. Syst. 63 (9) (2021)
Tomoya Murata, Taiji Suzuki
Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning. CoRR (2021)
Tomoya Murata, Taiji Suzuki
Gradient Descent in RKHS with Importance Labeling. AISTATS (2021)
Tomoya Murata, Taiji Suzuki
Gradient Descent in RKHS with Importance Labeling. CoRR (2020)
Taiji Suzuki, Hiroshi Abe, Tomoya Murata, Shingo Horiuchi, Kotaro Ito, Tokuma Wachi, So Hirai, Masatoshi Yukishima, Tomoaki Nishimura
Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error. IJCAI (2020)
Atsushi Nitanda, Tomoya Murata, Taiji Suzuki
Sharp Characterization of Optimal Minibatch Size for Stochastic Finite Sum Convex Optimization. ICDM (2019)
Tomoya Murata, Taiji Suzuki
Accelerated Sparsified SGD with Error Feedback. CoRR (2019)
Taiji Suzuki, Hiroshi Abe, Tomoya Murata, Shingo Horiuchi, Kotaro Ito, Tokuma Wachi, So Hirai, Masatoshi Yukishima, Tomoaki Nishimura
Spectral-Pruning: Compressing deep neural network via spectral analysis. CoRR (2018)
Tomoya Murata, Taiji Suzuki
Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation. NeurIPS (2018)
Tomoya Murata, Taiji Suzuki
Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation. CoRR (2018)
Tomoya Murata, Taiji Suzuki
Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization. CoRR (2017)
Tomoya Murata, Taiji Suzuki
Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization. NIPS (2017)
Tomoya Murata, Taiji Suzuki
Stochastic dual averaging methods using variance reduction techniques for regularized empirical risk minimization problems. CoRR (2016)
Tomoya Murata, Jungpil Shin
Hand Gesture and Character Recognition Based on Kinect Sensor. Int. J. Distributed Sens. Networks 10 (2014)