Talks

  • 06/2023: Talk of "Best-of-three-worlds Analysis for Linear Bandits with Follow-the-regularized-leader Algorithm" at ITCS Workshop. [link]

  • 11/2022: Talk of "Player-optimal Stable Regret for Bandit Learning in Matching Markets" at MSRA Theory Center. [link]

  • 07/2022: Talk of "Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback" on the CCF NCTCS Annual. [link]

  • 11/2021: Talk of "The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle" on the Classical Talk @QuACT. [link]

  • 07/2021: Here is the slides for my talk of the title "Online Learning to Rank with Click Models: An Overview" in the 2nd Workshop on Deep Reinforcement Learning for Information Retrieval at SIGIR'2021 (DRL4IR).

  • 03/2021: Talk of "Contextual Bandits with Long Retry Sequences" at Renmin University of China. [link]

  • 08/2019: Here is the slides for my thesis defense.