Tomoya Murata
10 papers · 2017–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (21) 💎 Century Club · Bronze
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Machine Learning
(10)
Optimization & Theory
(8)
Artificial Intelligence
(5)
Learning Paradigms · Artificial Intelligence
(4)
Mathematics & Optimization
(3)
Application Areas
(3)
Core Methods
(3)
Optimization
(3)
Deep Learning
(2)
Learning Paradigms · Machine Learning
(2)
Learning Types
(2)
Security & Privacy
(1)
Architectures
(1)
Core AI
(1)
Differential Privacy
(1)
Keywords
non-convex optimization
(3)
federated learning
(3)
variance reduction
(3)
distributed learning
(2)
stochastic gradient
(2)
communication complexity
(2)
gradient descent
(2)
distributed optimization
(2)
out-of-distribution generalization
(1)
stochastic gradient descent
(1)
differential privacy
(1)
minimax optimality
(1)
sample complexity
(1)
empirical risk minimization
(1)
reproducing kernel hilbert space
(1)
importance sampling
(1)
domain generalization
(1)
generalization error
(1)
neural network pruning
(1)
model compression
(1)
Papers
Clustered Invariant Risk Minimization
AISTATS 2025
SILVER: Single-loop variance reduction and application to federated learning
ICML 2024
Simple Minimax Optimal Byzantine Robust Algorithm for Nonconvex Objectives with Uniform Gradient Heterogeneity
ICLR 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
NeurIPS 2022
Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning
ICML 2021
Gradient Descent in RKHS with Importance Labeling
AISTATS 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
NeurIPS 2018
Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization
NeurIPS 2017