A Finite-Particle Convergence Rate for Stein Variational Gradient Descent
Lists
Only you see this
Abstract
We provide a first finite-particle convergence rate for Stein variational gradient descent (SVGD). Specifically, whenever the target distribution is sub-Gaussian with a Lipschitz score, SVGD with $n$ particles and an appropriate step size sequence drives the kernel Stein discrepancy to zero at an order $1/\sqrt{\log\log n}$ rate. We suspect that the dependence on $n$ can be improved, and we hope that our explicit, non-asymptotic proof strategy will serve as a template for future refinements.
BibTeX
@inproceedings{shi2023finite,
author = {Jiaxin Shi and Lester Mackey},
title = {{A Finite-Particle Convergence Rate for Stein Variational Gradient Descent}},
booktitle = {Advances in Neural Information Processing Systems},
year = {2023},
url = {https://openreview.net/forum?id=0eRDQQK2TW},
}