Yuliang Wang

Yuliang Wang is a Phillip Griffiths Assistant Research Professor of Mathematics at Duke University, affiliated with the Department of Mathematics. His research interests include applied mathematics, with a focus on stochastic algorithms, minmax optimization, diffusion models, sequential Monte Carlo, and related areas. He has collaborated with several faculty members, including Profs. Jianfeng Lu, Hongkai Zhao, and Jian-Guo Liu. Wang obtained his Ph.D. in Mathematics from Shanghai Jiao Tong University in 2025, advised by Prof. Lei Li, and his B.S. in Mathematics and Applied Mathematics (Zhiyuan Honors Program) from Shanghai Jiao Tong University in 2020. He has also held visiting scholar positions at Duke University and the University of California, Los Angeles.

Yuliang Wang is an applied mathematician whose research focuses on stochastic differential equations, numerical methods, and machine learning. His work explores topics such as stochastic gradient Langevin dynamics, diffusion approximations, and random batch methods for interacting particle systems. Wang's publications address uniform-in-time error estimates, geometric ergodicity, and convergence analysis for numerical schemes. He also investigates the application of information theory and relative entropy in the context of Langevin dynamics and particle filters. His research bridges theoretical analysis with practical algorithms, contributing to both mathematical theory and computational methods in data science.