High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm

MaRDI QIDQ6324348arXivFDO

Authors Wenlong Mou, Yi-An Ma, Martin J. Wainwright, Peter L. Bartlett, Michael Jordan

Publication date 28 August 2019

Mathematics Subject Classification ID

Bayesian inference (62F15) Monte Carlo methods (65C05) Numerical solutions to stochastic differential and integral equations (65C30)

Abstract: We propose a Markov chain Monte Carlo (MCMC) algorithm based on third-order Langevin dynamics for sampling from distributions with log-concave and smooth densities. The higher-order dynamics allow for more flexible discretization schemes, and we develop a specific method that combines splitting with more accurate integration. For a broad class of $d$-dimensional distributions arising from generalized linear models, we prove that the resulting third-order algorithm produces samples from a distribution that is at most $varepsilon>0$ in Wasserstein distance from the target distribution in $Oleft(frac{d}^{1/4}varepsilo{n}^{1/2}ight)$ steps. This result requires only Lipschitz conditions on the gradient. For general strongly convex potentials with $alpha$-th order smoothness, we prove that the mixing time scales as $Oleft(frac{d}^{1/4}varepsilo{n}^{1/2}+frac{d}^{1/2}varepsilo{n}^{1/(alpha-1)}ight)$.

This page was built for publication: High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6324348)