Coupling and Convergence for Hamiltonian Monte Carlo
From MaRDI portal
Publication:6301040
DOI10.1214/19-AAP1528arXiv1805.00452MaRDI QIDQ6301040FDOQ6301040
Authors: Nawaf Bou-Rabee, Andreas Eberle, Raphael Zimmer 
Publication date: 1 May 2018
Abstract: Based on a new coupling approach, we prove that the transition step of the Hamiltonian Monte Carlo algorithm is contractive w.r.t. a carefully designed Kantorovich (L1 Wasserstein) distance. The lower bound for the contraction rate is explicit. Global convexity of the potential is not required, and thus multimodal target distributions are included. Explicit quantitative bounds for the number of steps required to approximate the stationary distribution up to a given error are a direct consequence of contractivity. These bounds show that HMC can overcome diffusive behaviour if the duration of the Hamiltonian dynamics is adjusted appropriately.
Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Numerical methods for Hamiltonian systems including symplectic integrators (65P10)
This page was built for publication: Coupling and Convergence for Hamiltonian Monte Carlo
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6301040)
