Fang Kong

Best-of-three-worlds Analysis for Dueling Bandits with Borda Winner

Bandit Learning in Matching Markets Robust to Adversarial Corruptions

Player-optimal Stable Regret for Bandit Learning in Many-to-one Matching Markets with Substitutability

Bandit Learning in Matching Markets with Switching Cost

Hybrid Combinatorial Multi-armed Bandits with Probabilistically Triggered Arms

Regret Analysis of Hybrid Linear Bandits with Biased Offline Data

Learning Across the Gap: Hybrid Multi-armed Bandits with Heterogeneous Offline and Online Data

Bandit Learning in Matching Markets with Indifference