Using Perturbed Underdamped Langevin Dynamics to Efficiently Sample from Probability Distributions

Abstract

In this paper we introduce and analyse Langevin samplers that consist of perturbations of the standard underdamped Langevin dynamics. The perturbed dynamics is such that its invariant measure is the same as that of the unperturbed dynamics. We show that appropriate choices of the perturbations can lead to samplers that have improved properties, at least in terms of reducing the asymptotic variance. We present a detailed analysis of the new Langevin sampler for Gaussian target distributions. Our theoretical results are supported by numerical experiments with non-Gaussian target measures.

45 pages, 4 figures

References in corpus (3)

• Variance Reduction using Nonreversible Langevin Samplers
• Accelerating diffusions
• Irreversible Langevin samplers and variance reduction: a large deviation approach

Cited by in corpus (6)

• Role of current fluctuations in nonreversible samplers
• Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents
• Optimal friction matrix for underdamped Langevin sampling
• Stochastic gradient descent and fast relaxation to thermodynamic equilibrium: a stochastic control approach
• Pressure statistics from the path integral for Darcy flow through random porous media
• Random-batch list algorithm for short-range molecular dynamics simulations