معرفی
Wenlong Mou is an Assistant Professor at the University of Toronto's Department of Statistical Sciences, with additional affiliation at the Vector Institute for AI. His research develops optimal statistical methods and efficient algorithms for data-driven decision-making, focusing on reinforcement learning, stochastic approximation, and causal estimation. He teaches advanced courses in theoretical statistics (STA3000) and stochastic processes (STA447/2006).
Education:
- Ph.D. in EECS, University of California, Berkeley (2023)
- B.Sc. in Computer Science and Economics, Peking University
Research Focus: Mou's work bridges statistical theory with machine learning practice. Key areas include:
- Theoretical foundations of reinforcement learning (e.g., Bellman equations, continuous-time systems)
- Efficient algorithms for semi-parametric estimation and debiasing
- Non-asymptotic analysis of stochastic optimization and MCMC methods
- High-dimensional statistical inference and causal modeling
Publication Trends: Recent articles (2023–2025) emphasize reinforcement learning theory (policy evaluation, adaptive interpolation), causal inference (debiased estimators, propensity scores), and statistical computing (diffusion processes, Langevin algorithms). Methodological rigor and non-asymptotic guarantees characterize his work.
Awards:
- INFORMS APS Student Paper Competition Finalist (2022)
Advising and Labs: Actively recruiting PhD students with backgrounds in mathematics or deep learning. Students access GPU clusters via the Vector Institute. Grants unspecified in sources.
