06/12/2020

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

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

Keywords:

Abstract Paper Similar Papers

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.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at NeurIPS 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 13:42 
 0
 0
 1
 1
 15:08 
 0
 0
 0
 0
 15:00 
 0
 0
 0
 0
 16:03 
 0
 0
 0
 0
 3:14 
 0
 0
 0
 1
 3:22 
 0
 0
 0
 0
 17:31 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 15:01 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 3:33 
 0
 0
 1
 1
 3:21 
 0
 0
 0
 0
 18:01 
 0
 0
 0
 0
 2:56 
 0
 0
 0
 0
 14:22 
 0
 0
 0
 0
 14:47 
 0
 0
 0
 0
 3:16 
 0
 0
 0
 0
 9:07 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 5:20 
 0
 0
 0
 0
 14:57 
 0
 0
 0
 0
 4:49 
 0
 0
 0
 0
 11:43 
 0
 0
 0
 0
 5:41 
 0
 0
 0
 0
 10:13 
 0
 0
 0
 0
 14:24 
 0
 0
 0
 0
 5:40 
 0
 0
 0
 0
 4:24 
 0
 1
 2
 1
 14:43 
 0
 0
 0
 0
 2:52 
 0
 0
 0
 0
 13:43 
 0
 0
 0
 0
 21:23 
 0
 0
 0
 0
 15:16 
 0
 0
 0
 0
 8:30 
 0
 0
 0
 0
 11:21 
 0
 0
 0
 0
 13:31 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 1
 3:14