Simulated Tempering Langevin Monte Carlo II: An Improved Proof using Soft Markov Chain Decomposition

by   Rong Ge, et al.

A key task in Bayesian machine learning is sampling from distributions that are only specified up to a partition function (i.e., constant of proportionality). One prevalent example of this is sampling posteriors in parametric distributions, such as latent-variable generative models. However sampling (even very approximately) can be #P-hard. Classical results going back to Bakry and Émery (1985) on sampling focus on log-concave distributions, and show a natural Markov chain called Langevin diffusion mixes in polynomial time. However, all log-concave distributions are uni-modal, while in practice it is very common for the distribution of interest to have multiple modes. In this case, Langevin diffusion suffers from torpid mixing. We address this problem by combining Langevin diffusion with simulated tempering. The result is a Markov chain that mixes more rapidly by transitioning between different temperatures of the distribution. We analyze this Markov chain for a mixture of (strongly) log-concave distributions of the same shape. In particular, our technique applies to the canonical multi-modal distribution: a mixture of gaussians (of equal variance). Our algorithm efficiently samples from these distributions given only access to the gradient of the log-pdf. For the analysis, we introduce novel techniques for proving spectral gaps based on decomposing the action of the generator of the diffusion. Previous approaches rely on decomposing the state space as a partition of sets, while our approach can be thought of as decomposing the stationary measure as a mixture of distributions (a "soft partition"). Additional materials for the paper can be found at The proof and results have been improved and generalized from the precursor at


page 1

page 2

page 3

page 4


Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo

A key task in Bayesian statistics is sampling from distributions that ar...

Spectral Gap of Replica Exchange Langevin Diffusion on Mixture Distributions

Langevin diffusion (LD) is one of the main workhorses for sampling probl...

Modified log-Sobolev inequalities for strongly log-concave distributions

We show that the modified log-Sobolev constant for a natural Markov chai...

The Randomized Midpoint Method for Log-Concave Sampling

Sampling from log-concave distributions is a well researched problem tha...

Measuring Sample Quality with Diffusions

Standard Markov chain Monte Carlo diagnostics, like effective sample siz...

Online Sampling from Log-Concave Distributions

Given a sequence of convex functions f_0, f_1, ..., f_T, we study the pr...

Faster Sampling from Log-Concave Distributions over Polytopes via a Soft-Threshold Dikin Walk

We consider the problem of sampling from a d-dimensional log-concave dis...