Young Researchers Workshop: Kinetic descriptions in theory and applications

Scaling limit analysis of Stein variational gradient descent

Yulong Lu

Duke University

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.