Taira Tsuchiya

17 papers · 2020–2025 · 5 conferences · across top CS/AI conferences

Achievements

🏃 Academic Marathon (5) 🗺️ Taxonomy Completionist (19) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (14) 🌍 Conference Polyglot (5) 🤝 Dynamic Duo (12) 💎 Century Club (17) ⚡ Prolific Year (6)

Conferences

NIPS (6) COLT (5) AISTATS (3) ALT (2) ICML (1)

Top co-authors

Shinji Ito (12) Junya Honda (10) Han Bao (2) Haipeng Luo (2) Shinsaku Sakaue (2) Junpei Komiyama (1) Yue Wu (1) Fabio Vitale (1) Alberto Rumi (1) Yuko Kuroki (1)

Research topics

Learning Paradigms (1)

Keywords

regret bound (10) multi-armed bandit (7) stochastic regime (3) stochastic optimization (3) online learning (3) partial monitoring (2) follow the regularized leader (2) adversarial corruption (2) thompson sampling (2) bandit algorithm (2) minimax optimality (1) adaptive learning rate (1) logistic loss (1) best arm identification (1) bayesian optimization (1) sample complexity (1) adversarial learning (1) logarithmic regret (1) learning rate (1) online convex optimization (1)

Papers

Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel–Young Loss Perspective and Gap-Dependent Regret Analysis AISTATS 2025

Corrupted Learning Dynamics in Games COLT 2025

Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback COLT 2025

Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring ICML 2024

A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds NIPS 2024

Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets NIPS 2024

Best-of-Both-Worlds Algorithms for Linear Contextual Bandits AISTATS 2024

Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds COLT 2024

Online Structured Prediction with Fenchel–Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss COLT 2024

Follow-the-Perturbed-Leader Achieves Best-of-Both-Worlds for Bandit Problems ALT 2023

Best-of-Both-Worlds Algorithms for Partial Monitoring ALT 2023

Further Adaptive Best-of-Both-Worlds Algorithm for Combinatorial Semi-Bandits AISTATS 2023

Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds NIPS 2023

Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs NIPS 2022

Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds COLT 2022

Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification NIPS 2022

Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring NIPS 2020