High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm

arXiv1908.10859MaRDI QIDQ6324348FDOQ6324348

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

Publication date: 28 August 2019

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 $Oleft(frac{d}^{1/4}varepsilo{n}^{1/2}+frac{d}^{1/2}varepsilo{n}^{1/(alpha-1)}ight)$.

Mathematics Subject Classification ID

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

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)