Skip to content

Stein Variational Gradient Descent with Matrix-Valued Kernels

Notifications You must be signed in to change notification settings

dilinwang820/matrix_svgd

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Matrix SVGD

In this work, we enhance SVGD by leveraging preconditioning matrices, such as the Hessian and Fisher information matrix, to incorporate geometric information into SVGD updates. We achieve this by presenting a generalization of SVGD that replaces the scalar-valued kernels in vanilla SVGD with more general matrix-valued kernels. This yields a significant extension of SVGD, and more importantly, allows us to flexibly incorporate various preconditioning matrices to accelerate the exploration in the probability landscape.

How to reproduce our results?

  cd *example-folder*

About

Stein Variational Gradient Descent with Matrix-Valued Kernels

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published