NeurIPS 2020poster90 citations

SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence

Sinho Chewi, Thibaut Le Gouic, Chen Lu, Tyler Maunu, Philippe Rigollet

Abstract

Stein Variational Gradient Descent (SVGD), a popular sampling algorithm, is often described as the kernelized gradient flow for the Kullback-Leibler divergence in the geometry of optimal transport. We introduce a new perspective on SVGD that instead views SVGD as the kernelized gradient flow of the chi-squared divergence. Motivated by this perspective, we provide a convergence analysis of the chi-squared gradient flow. We also show that our new perspective provides better guidelines for choosing effective kernels for SVGD.

BibTeX
@inproceedings{NEURIPS2020_16f8e136,
 author = {Chewi, Sinho and Le Gouic, Thibaut and Lu, Chen and Maunu, Tyler and Rigollet, Philippe},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
 pages = {2098--2109},
 publisher = {Curran Associates, Inc.},
 title = {SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence},
 url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/16f8e136ee5693823268874e58795216-Paper.pdf},
 volume = {33},
 year = {2020}
}
SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence · NeurIPS 2020