論文表記の著者名
Shinji Ito
東京大学Machine Learning2022–2026 LIVE
対象論文 19 本
著者名は論文に記載された表記をそのまま使用しており、同一人物の名寄せは行っていません。
印刷日： 全論文
論文上の著者表記・公開時所属による集計です。人物の名寄せ・現在所属・全業績を表すものではありません。
対象論文
論文一覧
- A Tight Lower Bound for Non-stochastic Multi-armed Bandits with Expert Advice
- Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader
- Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret
- Submodular Function Minimization with Dueling Oracle
- A Perturbation Approach to Unconstrained Linear Bandits
- Last-Iterate Convergence of Regularized Gradient Methods for Stochastic Monotone Variational Inequalities
- Corrupted Learning Dynamics in Games
- Data-dependent Bounds with $T$-Optimal Best-of-Both-Worlds Guarantees in Multi-Armed Bandits using Stability-Penalty Matching
- Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback
- Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
- Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
- Optimal Regret of Bandits under Differential Privacy
- Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
- Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds
- Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds
- Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
- 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
- Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
- On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice