Stein Variational Gradient Descent Without Gradient

06/07/2018
by   Jun Han, et al.
0

Stein variational gradient decent (SVGD) has been shown to be a powerful approximate inference algorithm for complex distributions. However, the standard SVGD requires calculating the gradient of the target density and cannot be applied when the gradient is unavailable. In this work, we develop a gradient-free variant of SVGD (GF-SVGD), which replaces the true gradient with a surrogate gradient, and corrects the induced bias by re-weighting the gradients in a proper form. We show that our GF-SVGD can be viewed as the standard SVGD with a special choice of kernel, and hence directly inherits the theoretical properties of SVGD. We shed insights on the empirical choice of the surrogate gradient and propose an annealed GF-SVGD that leverages the idea of simulated annealing to improve the performance on high dimensional complex distributions. Empirical studies show that our method consistently outperforms a number of recent advanced gradient-free MCMC methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/13/2021

Stein variational gradient descent with local approximations

Bayesian computation plays an important role in modern machine learning ...
research
03/07/2020

Scalable Approximate Inference and Some Applications

Approximate inference in probability models is a fundamental task in mac...
research
02/13/2022

Understanding Natural Gradient in Sobolev Spaces

While natural gradients have been widely studied from both theoretical a...
research
02/21/2020

Stein Self-Repulsive Dynamics: Benefits From Past Samples

We propose a new Stein self-repulsive dynamics for obtaining diversified...
research
07/20/2021

Kernel Selection for Stein Variational Gradient Descent

Stein variational gradient descent (SVGD) and its variants have shown pr...
research
06/26/2018

Guided evolutionary strategies: escaping the curse of dimensionality in random search

Many applications in machine learning require optimizing a function whos...
research
06/20/2021

On Stein Variational Neural Network Ensembles

Ensembles of deep neural networks have achieved great success recently, ...

Please sign up or login with your details

Forgot password? Click here to reset