Mathematical Optimization
First-order methods and complexity theory for nonsmooth, stochastic, and minimax optimization in Euclidean and non-Euclidean geometries.
I am a tenure-track assistant professor in the Operations & Logistics Division at the Sauder School of Business, University of British Columbia. I am also a faculty member of the Institute of Applied Mathematics (IAM) and an associate member of the Department of Computer Science at UBC.
Previously, I was a postdoctoral researcher in the Department of Management Science and Engineering (MS&E) at Stanford University, hosted by Prof. Jose Blanchet. I received my Ph.D. from the Department of Systems Engineering and Engineering Management at the Chinese University of Hong Kong (CUHK) in 2021, where I was advised by Prof. Anthony Man-Cho So.
First-order methods and complexity theory for nonsmooth, stochastic, and minimax optimization in Euclidean and non-Euclidean geometries.
Provable, efficient, and geometry-aware algorithms for large-scale optimization and decision-making problems.
First-principles design of efficient optimizers for stable and scalable training of large language models.
Exploring AI agents for mathematical reasoning and optimization. Hard-instance discovery for optimization lower bounds serves as a testbed for continual learning and skill accumulation.