Nonreversible Langevin Samplers: Splitting Schemes, Analysis and Implementation

Abstract

For a given target density, there exist an infinite number of diffusion processes which are ergodic with respect to this density. As observed in a number of papers, samplers based on nonreversible diffusion processes can significantly outperform their reversible counterparts both in terms of asymptotic variance and rate of convergence to equilibrium. In this paper, we take advantage of this in order to construct efficient sampling algorithms based on the Lie-Trotter decomposition of a nonreversible diffusion process into reversible and nonreversible components. We show that samplers based on this scheme can significantly outperform standard MCMC methods, at the cost of introducing some controlled bias. In particular, we prove that numerical integrators constructed according to this decomposition are geometrically ergodic and characterise fully their asymptotic bias and variance, showing that the sampler inherits the good mixing properties of the underlying nonreversible diffusion. This is illustrated further with a number of numerical examples ranging from highly correlated low dimensional distributions, to logistic regression problems in high dimensions as well as inference for spatial models with many latent variables.

References in corpus (5)

• A Complete Recipe for Stochastic Gradient MCMC
• The computation of averages from equilibrium and nonequilibrium Langevin molecular dynamics
• Optimal non-reversible linear drift for the convergence to equilibrium of a diffusion
• Variance Reduction using Nonreversible Langevin Samplers
• Generalized and hybrid Metropolis-Hastings overdamped Langevin algorithms

Cited by in corpus (9)

• Modified Hamiltonian Monte Carlo for Bayesian inference
• Response Theory and Phase Transitions for the Thermodynamic Limit of Interacting Identical Systems
• Breaking Reversibility Accelerates Langevin Dynamics for Global Non-Convex Optimization
• Non-reversible Markov chain Monte Carlo for sampling of districting maps
• Non-Convex Optimization via Non-Reversible Stochastic Gradient Langevin Dynamics
• Hypoelliptic entropy dissipation for stochastic differential equations
• A Unifying and Canonical Description of Measure-Preserving Diffusions
• Non-reversible sampling schemes on submanifolds
• Entropy dissipation via Information Gamma calculus: Non-reversible stochastic differential equations