Skip to main content
Browse by:

Scaling limit analysis of Stein variational gradient descent

Duke Math Logo
Monday, August 20, 2018
11:00 am - 12:00 pm
Yulong Lu (Duke University)
Applied Math And Analysis Seminar

The Stein variational gradient descent (SVGD) was proposed by Liu and Wang as a deterministic algorithm for sampling from a given probability density with unknown normalization. The key idea is to involve a system of interacting particles in an optimized way so that the empirical measure approximates a target distribution. In this talk, I will first introduce the algorithm and compare it with some stochastic-dynamics-based sampling methods. I will also present some recent rigorous analysis results on the mean field limit and long time behavior of the resulting mean field partial differential equation. This is a joint work with Jianfeng Lu and James Nolen.