Talks

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).

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