Convergence of preconditioned Hamiltonian Monte Carlo on Hilbert spaces

DOI10.1093/IMANUM/DRAC052MaRDI QIDQ6190813zbMATH OpenOpenAlexFDO

Authors Jakiw Pidstrigach

Publication date 6 February 2024

Published in IMA Journal of Numerical Analysis (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2011.08578

zbMATH Keywords

Metropolis-HastingsHamiltonian Monte CarloWasserstein distancepreconditioningcouplinggeometric integrationHilbert spaceshybrid Monte Carloconvergence to equilibriumMarkov chain Monte Carlo in infinite dimensions

Mathematics Subject Classification ID

Monte Carlo methods (65C05) General theory of numerical analysis in abstract spaces (65J05) Numerical solutions to equations with linear operators (65J10)

Abstract: In this article, we consider the preconditioned Hamiltonian Monte Carlo (pHMC) algorithm defined directly on an infinite-dimensional Hilbert space. In this context, and under a condition reminiscent of strong log-concavity of the target measure, we prove convergence bounds for adjusted pHMC in the standard 1-Wasserstein distance. The arguments rely on a synchronous coupling of two copies of pHMC, which is controlled by adapting elements from arXiv:1805.00452.

Recommendations

• Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions
• Mixing rates for Hamiltonian Monte Carlo algorithms in finite and infinite dimensions
• On \(L^2\) convergence of the Hamiltonian Monte Carlo
• Hybrid Monte Carlo on Hilbert spaces
• On \(L^\mathfrak{q}\) convergence of the Hamiltonian Monte Carlo

This page was built for publication: Convergence of preconditioned Hamiltonian Monte Carlo on Hilbert spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6190813)