Jianfeng Lu, Duke University, USA
Conference ID: 709-671-276
PIN Code: 811895
Sampling algorithms based on underdamped Langevin dynamics has been quite popular in computational statistical mechanics, Bayesian statistic, and machine learning. In this talk, we will discuss two recent results on theoretical understanding of the underdamped Langevin dynamics. We establish a sharp L^2-convergence rate to equilibrium and also the complexity lower bound for discretizing the underdamped Langevin dynamics based on queries to gradient and the driven noise.The talk is based on joint works with Yu Cao and Lihan Wang, both graduate students at Duke.
Jianfeng Lu is currently a Professor of Mathematics, Physics, and Chemistry at Duke University. Before joining Duke University, he obtained his PhD in Applied Mathematics from Princeton University in 2009 and was a Courant Instructor at New York University from 2009 to 2012. He works in mathematical analysis and algorithm development for problems and challenges arising from computational physics, theoretical chemistry, materials science, high-dimensional PDEs, and machine learning. His work has been recognized by a Sloan Fellowship, a NSF Career Award, and the 2017 IMA Prize in Mathematics and its Applications.