Wenlong Mou (牟文龙)
About me
Welcome to my homepage!
I am a finalyear Ph.D. student at Department of EECS, UC Berkeley. I'm very fortunate to be advised by Prof. Martin Wainwright and Prof. Peter Bartlett. Prior to Berkeley, I received B.S. in Computer Science from Peking University in 2017, where I was very fortunate to work with Prof. Liwei Wang.
Starting from Fall 2023, I will join the Department of Statistical Sciences at University of Toronto as an Assistant Professor!
Research
My research interests are broadly in statistics, machine learning theory, dynamic programming and optimization, and applied probability. In particular, I develop optimal statistical methods that enable optimal decision making, powered with efficient computational algorithms. Currently, I work on the following topics:
Theory of reinforcement learning with function approximation, geometry of Bellman equations, statistical complexity of reinforcement learning
Nonasymptotic theory of semiparametric statistics, finitesample optimal methods for treatment effect estimation
Stochastic approximation algorithms under statistical settings, interplay between geometry, stochastic processes and optimization
Discretization of diffusion processes, highdimensional MCMC algorithms, Bayesian posterior contraction
News
Mar 2023: New paper on debiased IPW estimator in high dimensions.
Jan 2023: New paper on instancedependent optimality for offpolicy estimation beyond semiparametric efficiency bound.
Sep 2022: Paper on projected fixedpoint accepted to Mathematics of Operations Research
Sep 2022: New paper on nonasymptotic theory for semiparametric efficiency.
Sep 2022: Paper on nonsmooth MCMC accepted to Journal of Machine Learning Research
Sep 2022: Paper on Markovian stochastic approximation selected as a finalist for INFORMS Applied Probability Society Best Student Paper competition
