← Authors

Tomoya Murata

10 papers · 2017–2025 · 5 conferences · across top CS/AI conferences

Achievements

πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌈 Renaissance Researcher (5) πŸ—ΊοΈ Taxonomy Completionist (18) 🌍 Conference Polyglot (5) πŸƒ Academic Marathon (8) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (11) πŸ’Ž Century Club (10) πŸ”₯ Unstoppable (6)

Conferences

ICML (3) NIPS (3) AISTATS (2) ICLR (1) IJCAI (1)

Top co-authors

Taiji Suzuki (9) Shunta Akiyama (1) Takumi Fukami (1) Hiroshi Abe (1) Tomoaki Nishimura (1) Iifan Tyou (1) Denny Wu (1) Shingo Horiuchi (1) Kenta Niwa (1) Atsushi Nitanda (1)

Research topics

Differential Privacy (1)

Keywords

distributed optimization (2) federated learning (2) nonconvex optimization (2) stochastic gradient (2) gradient descent (2) communication complexity (2) variance reduction (2) distributed learning (2) generalization error (1) spectral analysis (1) dual averaging (1) restricted eigenvalue (1) least squares regression (1) communication efficiency (1) sparse linear regression (1) accelerated gradient (1) saddle point (1) iterative method (1) iterative hard thresholding (1) hard thresholding (1)

Papers

Clustered Invariant Risk Minimization AISTATS 2025
Simple Minimax Optimal Byzantine Robust Algorithm for Nonconvex Objectives with Uniform Gradient Heterogeneity ICLR 2024
SILVER: Single-loop variance reduction and application to federated learning ICML 2024
DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning ICML 2023
Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning NIPS 2022
Gradient Descent in RKHS with Importance Labeling AISTATS 2021
Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning ICML 2021
Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error IJCAI 2020
Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation NIPS 2018
Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization NIPS 2017