An Efficient Sampling Algorithm for Non-smooth Composite Potentials

10/01/2019
by   Wenlong Mou, et al.
24

We consider the problem of sampling from a density of the form p(x) ∝(-f(x)- g(x)), where f: R^d →R is a smooth and strongly convex function and g: R^d →R is a convex and Lipschitz function. We propose a new algorithm based on the Metropolis-Hastings framework, and prove that it mixes to within TV distance ε of the target density in at most O(d log (d/ε)) iterations. This guarantee extends previous results on sampling from distributions with smooth log densities (g = 0) to the more general composite non-smooth case, with the same mixing time up to a multiple of the condition number. Our method is based on a novel proximal-based proposal distribution that can be efficiently computed for a large class of non-smooth functions g.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/20/2022

A Proximal Algorithm for Sampling from Non-convex Potentials

We study sampling problems associated with non-convex potentials that me...
research
06/23/2023

On a Class of Gibbs Sampling over Networks

We consider the sampling problem from a composite distribution whose pot...
research
04/21/2022

Optimal Scaling for the Proximal Langevin Algorithm in High Dimensions

The Metropolis-adjusted Langevin (MALA) algorithm is a sampling algorith...
research
10/07/2020

Structured Logconcave Sampling with a Restricted Gaussian Oracle

We give algorithms for sampling several structured logconcave families t...
research
06/10/2020

Composite Logconcave Sampling with a Restricted Gaussian Oracle

We consider sampling from composite densities on ℝ^d of the form dπ(x) ∝...
research
01/22/2022

The Forward-Backward Envelope for Sampling with the Overdamped Langevin Algorithm

In this paper, we analyse a proximal method based on the idea of forward...
research
02/28/2022

A Proximal Algorithm for Sampling

We consider sampling problems with possibly non-smooth potentials (negat...

Please sign up or login with your details

Forgot password? Click here to reset