Advertisement: Looking to hire motivated postdocs. Please see this advertisement for more details.
Sep 2025: Paper "Parameter-free Algorithms for the Stochastically Extended Adversarial Model" accepted to NeurIPS 2025. Joint work with PhD student Shuche Wang, former postdoc Adarsh Barik, and collaborator Peng Zhao. The paper presents new parameter-free algorithms for the Stochastically Extended Adversarial (SEA) model, eliminating the need for pre-determined parameters by leveraging the Optimistic Online Newton Step (OONS) algorithm. These methods are applicable even when no prior knowledge of the Lipschitz constant or domain diameter exists.
Aug 2025: Appointed as a Senior Program Committee Member of AAAI 2026.
Aug 2025: Appointed to the University Teaching Excellence Committee (UTEC). This committee is responsible for selecting the recipients of teaching awards at the university level.
Jul 2025: Reappointed to the University Promotion and Tenure Committee (UPTC).
Online Decision Making, Multi-Armed Bandits, Reinforcement Learning Information Theory with Applications to Machine Learning Statistical Signal Processing
There are also multiple positions for talented
postdoctoral scholars. Postdoctoral scholars with strong publication records
and showing interest in the above research topics are also encouraged to
contact me to check with me if there are available positions. Please see this advertisement as well as this.
Best Arm Identification with Possibly Biased Offline Data Le Yang, Vincent Y. F. Tan, and Wang Chi Cheung
Proc. of the 41st Conference on Uncertainty in Artificial Intelligence (UAI), Rio de Janeiro, Brazil, Jul 2025 (AR ≈ 30.7%)
BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms [Poster] [Slides]
Yunlong Hou, Fengzhuo Zhang, Cunxiao Du, Xuan Zhang, Jiachun Pan, Tianyu Pang, Chao Du, Vincent Y. F. Tan, and Zhuoran Yang
Proc. of the 42nd International Conference on Machine Learning (ICML), Vancouver, Canada, Jul 2025 (AR ≈ 26.9%)