I am a Postdoc with Prof. Daniel Kuhn at the College of Management of Technology from EPFL and Prof. Andreas Krause at the Computer Science Department from ETH Zurich. Prior to that, I got my PhD in Operations Research from University of Illinois at Urbana-Champaign, advised by Prof. Xin Chen and Prof. Niao He.

My research interest lies in data-driven decision-making with problems arising from optimization, operations research, and data science. Specifically, I am interested in designing simple and efficient algorithms for stochastic optimization, robust learning, bandit and reinforcement learning with provable guarantees. I am also interested in operations management like supply chain and revenue management. See Research for research directions and Publication for papers and slides.

Google Scholar

Incoming Talks

- - Jul 2024, I will give a talk at International Symposium on Mathematical Programming in Montreal, Canada.

News

Jun. 2024, one preprint online.
- - Stochastic Bilevel Optimization with Lower-Level Contextual Markov Decision Processes.
    - - TL;DR: How to design environments of MDPs for multiple players to achieve robustness, exploration, imitation, and personalization.
May. 2024, two preprints online.
- - Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Data.
    - - TL;DR: Formulating instrumental variable regression as optimization, you can avoid the first stage in the two stage regression.
  - Group Robust Preference Optimization in Reward-free Reinforcement Learning with Human Feedback.
    - - TL;DR: When there are multiple data sources, how to train a LLM that performs well on all of them.
Apr. 2024, our proposal got approved by NCCR Automation from SNSF, Switzerland.
- - It supports a PhD for four years.
Mar. 2024, I organized a session and gave a talk at INFORMS Optimization Society Conference in Houston.
- - Session: Decision Making with Side Information.
  - Talk: Contextual Stochastic Bilevel Optimization. Here are the Slides.
Feb. 2024, we got a minor revision at Operations Research!
- - Efficient Algorithms for Minimizing Compositions of Convex Functions and Random Functions and Its Applications in Network Revenue Management. Here are the Slides.
Jan. 2024, two papers got accepted to AISTATS 2024!
- - Generalization Bounds of Nonconvex-(Strongly)-Concave Stochastic Minimax Optimization.
  - Distributionally Robust Model-based Reinforcement Learning with Large State Spaces.
Dec. 2023, one paper about hidden convexity is online.
- - Stochastic Optimization under Hidden Convexity.
Oct. 2023, I organized a session and gave a talk at at INFORMS Annual Meeting in Phoenix, AZ.
- - Session: Distributionally Robust Learning.
  - Talk: Contextual Stochastic Bilevel Optimization.
Sep. 2023, one paper got accepted to NeurIPS 2023!
- - Contextual Stochastic Bilevel Optimization.