Changxiao Cai
 |
I am an assistant professor of Industrial and Operations Engineering and an affiliate faculty member of Electrical and Computer
Engineering at University of Michigan. Previously, I was a postdoctoral researcher at University of Pennsylvania, advised by T. Tony Cai and Hongzhe Li. I obtained my Ph.D. in Electrical Engineering at Princeton University in 2021, advised by Yuxin Chen and H. Vincent Poor. I have also worked with Sergio Verdú at Princeton. Prior to this, I received my B.E. in Electronic Engineering from Tsinghua University in 2016. I am broadly interested in mathematical data science, with a recent focus on diffusion model, reinforcement learning, high-dimensional statistics, and nonconvex optimization.
E-mail: cxcai [at] umich [dot] edu |
News
A new paper on (nearly) dimension-free convergence of DDPM for approximate GMMs: Dimension-Free Convergence of Diffusion Models for Approximate Gaussian Mixtures
A new paper on minimax optimality of ODE-based samplers in diffusion models: Minimax Optimality of the Probability Flow ODE for Diffusion Models
A new paper on acceleration for diffusion models: Provable Acceleration for Diffusion Models under Minimal Assumptions
A new paper on the trust-aware multi-armed bandit: Minimax-Optimal Trust-Aware Multi-Armed Bandits