ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Shinji Ito

Shinji Ito

Topic trends: 31,945 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,180 papers | Abstracts: 31,002 (90.7%) | Citations: 34,180 (100.0%) | arXiv: 25,731 (75.3%)

Built: Feb 8, 2026, 12:39 PM AMS

16

papers

3

total citations

papers (16)

Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems

NeurIPS 2025arXiv

Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback

NeurIPS 2025arXiv

Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning

NeurIPS 2025arXiv

New Classes of the Greedy-Applicable Arm Feature Distributions in the Sparse Linear Bandit Problem

Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring

Tight First- and Second-Order Regret Bounds for Adversarial Linear Bandits

Delay and Cooperation in Nonstochastic Linear Bandits

A Tight Lower Bound and Efficient Reduction for Swap Regret

Hybrid Regret Bounds for Combinatorial Semi-Bandits and Adversarial Linear Bandits

On Optimal Robustness to Adversarial Corruption in Online Decision Problems

NeurIPS 2021arXiv

Single Loop Gaussian Homotopy Method for Non-convex Optimization

NeurIPS 2022arXiv

Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs

NeurIPS 2022arXiv

Average Sensitivity of Euclidean k-Clustering

Bandit Task Assignment with Unknown Processing Time

Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds

NeurIPS 2023arXiv

An Exploration-by-Optimization Approach to Best of Both Worlds in Linear Bandits