I am a postdoc at University of Massachusetts - Amherst, working with Don Towsley and Mohammad Hajiesmaili. I received my Ph.D. in the Department of Computer Science & Engineering at The Chinese University of Hong Kong under the guidance of John C.S. Lui.
My research is dedicated to designing algorithms for sequential decision-making under uncertainty, with a particular focus on online learning algorithms incorporating multi-armed bandit feedback and distributed multi-agent cooperation.
- NeurIPSMulti-Fidelity Multi-Armed Bandits RevisitedIn Advances in Neural Information Processing Systems , 2023
- ICLRAchieve Near-Optimal Individual Regret & Low Communications in Multi-Agent BanditsIn International Conference on Learning Representations , 2023
- ICMLMultiple-Play Stochastic Bandits with Shareable Finite-Capacity ArmsIn Proceedings of the 39th International Conference on Machine Learning , 2022