Journal Publications
- Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits Under Realizability (with David Simchi-Levi)
- Mathematics of Operations Research (2022)
- Honorable Mention, INFORMS George Nicholson Student Paper Competition, 2020
- Online Pricing with Offline Data: Phase Transition and Inverse Square Law (with Jinzhi Bu and David Simchi-Levi)
- Management Science (2022)
- Preliminary version appeared in ICML 2020
- Winner, INFORMS Data Mining Best Theoretical Paper Award, 2020
- Phase Transitions in Bandits with Switching Constraints (with David Simchi-Levi)
- Management Science (2023)
- Preliminary version appeared in NeurIPS 2019
- Finalist, Applied Probability Society Best Student Paper Award, 2019
- Assortment Optimization for a Multi-Stage Choice Model (with Zizhuo Wang)
- Manufacturing & Service Operations Management (2023)
- Finalist, INFORMS Undergraduate Operations Research Prize, 2018
Journal Papers Under Revision
- Blind Network Revenue Management and Bandits with Knapsacks Under Limited Switches (with David Simchi-Levi and Jinglong Zhao)
- Minor Revision, Operations Research
- Finalist, IBM Service Science Best Student Paper Award, 2021
Working Papers
- Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation (with Dylan Foster, Akshay Krishnamurthy, David Simchi-Levi)
- Journal version to be submitted
- Conference version accepted to COLT 2022
- Oral Presentation, NeurIPS 2021 Offline Reinforcement Learning Workshop
- Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective (with Dylan Foster, Alexander Rakhlin, David Simchi-Levi)
- Journal version to be submitted
- Conference version accepted to COLT 2021
- Feature-Based Dynamic Pricing with Online Learning and Offline Data (with Jinzhi Bu, David Simchi-Levi, and Sabrina Zhai)
- Journal version in preparation
- Finalist, INFORMS RMP Jeff McGill Student Paper Award, 2022
A list of the research talks that I gave can be found here.