My research interests lie in online decision-making theory (e.g., online learning and online matching), with applications to revenue and supply chain management.

Publications and Preprints

• Regret Distribution in Stochastic Bandits: Optimal Trade-off between Expectation and Tail Risk, with David Simchi-Levi and Zeyu Zheng.
  • Preliminary version accepted by NeurIPS 2023 (Spotlight)
• A Simple and Optimal Policy Design with Safety against Heavy-tailed Risk for Stochastic Bandits, with David Simchi-Levi and Zeyu Zheng.
  • Preliminary version accepted by NeurIPS 2022
• On Greedy-like Policies in Online Matching with Reusable Network Resources and Decaying Rewards, with David Simchi-Levi and Zeyu Zheng.
• Offline Planning and Online Learning under Recovering Rewards, with David Simchi-Levi and Zeyu Zheng.
  • Management Science
  • Preliminary version accepted by ICML 2021
• Dynamic Pricing in a Non-stationary Growing Environment, with Zeyu Zheng.
  • Preliminary version accepted by ICML 2020
• Assign-to-Seat: Dynamic Capacity Control for Selling High-Speed Train Tickets, with Shaoxuan Liu, Rowan Wang and Zizhuo Wang.
  • Manufacturing & Service Operations Management