土屋 平

Corrupted Learning Dynamics in Games 

Conference on Learning Theory (COLT), to appear abs/2412.07120 2025年6月  査読有り筆頭著者責任著者

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

Conference on Learning Theory (COLT), to appear 2025年6月  査読有り

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

AISTATS 2025年1月  査読有り

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 

Advances in Neural Information Processing Systems 37 (NeurIPS) 2024年12月  査読有り筆頭著者責任著者

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

Advances in Neural Information Processing Systems 37 (NeurIPS) 2024年  査読有り筆頭著者責任著者

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

Forty-first International Conference on Machine Learning (ICML) 2024年  査読有り筆頭著者責任著者

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

The Thirty Seventh Annual Conference on Learning Theory (COLT) 4458-4486 2024年  査読有り

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

The Thirty Seventh Annual Conference on Learning Theory (COLT) 2522-2563 2024年  査読有り

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

International Conference on Artificial Intelligence and Statistics (AISTATS) 1216-1224 2024年  査読有り

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

Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023 (NeurIPS) 2023年  査読有り筆頭著者責任著者

Best-of-Both-Worlds Algorithms for Partial Monitoring 

International Conference on Algorithmic Learning Theory (ALT) 1484-1515 2023年  査読有り筆頭著者責任著者

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

International Conference on Algorithmic Learning Theory (ALT) 726-754 2023年  査読有り

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

International Conference on Artificial Intelligence and Statistics (AISTATS) 8117-8144 2023年  査読有り筆頭著者責任著者

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

Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022 (NeurIPS) 2022年12月  査読有り

Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification 

Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022 (NeurIPS) 2022年  査読有り

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

Conference on Learning Theory (COLT) 1421-1422 2022年  査読有り

Semisupervised Ordinal Regression Based on Empirical Risk Minimization 

Neural Computation 33(12) 3361-3412 2021年  査読有り筆頭著者責任著者

Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring 

Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 (NeurIPS) 2020年  査読有り筆頭著者責任著者

Speaker Invariant Feature Extraction for Zero-Resource Languages with Adversarial Learning 

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2381-2385 2018年  査読有り筆頭著者