Unadjusted Langevin algorithm for sampling a mixture of weakly smooth potentials

12/17/2021
by   Dao Nguyen, et al.
0

Discretization of continuous-time diffusion processes is a widely recognized method for sampling. However, it seems to be a considerable restriction when the potentials are often required to be smooth (gradient Lipschitz). This paper studies the problem of sampling through Euler discretization, where the potential function is assumed to be a mixture of weakly smooth distributions and satisfies weakly dissipative. We establish the convergence in Kullback-Leibler (KL) divergence with the number of iterations to reach ϵ-neighborhood of a target distribution in only polynomial dependence on the dimension. We relax the degenerated convex at infinity conditions of <cit.> and prove convergence guarantees under Poincaré inequality or non-strongly convex outside the ball. In addition, we also provide convergence in L_β-Wasserstein metric for the smoothing potential.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/31/2023

Non-convex sampling for a mixture of locally smooth potentials

The purpose of this paper is to examine the sampling problem through Eul...
research
01/16/2021

Non-convex weakly smooth Langevin Monte Carlo using regularization

Discretization of continuous-time diffusion processes is a widely recogn...
research
05/27/2020

On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness

We study sampling from a target distribution ν_* = e^-f using the unadju...
research
07/10/2021

Convergence Analysis of Schrödinger-Föllmer Sampler without Convexity

Schrödinger-Föllmer sampler (SFS) is a novel and efficient approach for ...
research
05/04/2018

Sharp Convergence Rates for Langevin Dynamics in the Nonconvex Setting

We study the problem of sampling from a distribution where the negative ...
research
06/16/2020

Hessian-Free High-Resolution Nesterov Accelerationfor Sampling

We propose an accelerated-gradient-based MCMC method. It relies on a mod...
research
02/16/2023

Improved Discretization Analysis for Underdamped Langevin Monte Carlo

Underdamped Langevin Monte Carlo (ULMC) is an algorithm used to sample f...

Please sign up or login with your details

Forgot password? Click here to reset