I am a final-year Ph.D. candidate in Operations Research at Cornell University, advised by Professor Nathan Kallus at Cornell Tech. I obtained my B.S. in Mathematics and Applied Mathematics and B.A. in Economics from Peking University in 2017.

My research lies at the intersection of machine learning, stochastic optimization, and statistics. Specifically, I study the statistical limits of data-driven decision-making, working to understand when and how we can design fast and reliable personalized algorithms. My works draw inspiration from important real-world applications, including healthcare and online platforms.

I strive to identify cutting-edge problems and generate real-world impact through industry collaborations. In Summer 2021, I worked as a research engineer intern in the Adaptive Experimentation team at Meta, where I developed new methods for multi-objective adaptive experiments. In Summer 2020, I worked as a data scientist intern at Google Play, where I investigated causal models for customer retention.

I am on the 2022-2023 job market!

I will be presenting at the 2022 INFORMS Annual Meeting:

• Session: SB56. Data-driven decisions and applications
  • Title: Fast Rates For Contextual Linear Optimization
  • Time: October 16, 2022, 11:00 AM - 12:15 PM (4th talk)
  • Location: M - Marriott 3