The University of Tokyo · Graduate School of Information Science and Technology · 助教

Research keywordsバンディット問題・オンライン凸最適化・線形バンディット・コンテキスト付きバンディット・強化学習

This is a public-data preview. Personalized fit, contact angles, and saved workflows require sign-in.

• Bandit Max-Min Fair Allocation.2025
• Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds.2024
• Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring.2024
• Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds.2024

• 部分的フィードバックに基づくオンライン凸最適化2020
• 部分的フィードバックに基づくオンライン凸最適化2018

• Official profile