Affiliation:
1. Institute of Mathematics, Universität Potsdam , Karl-Liebknecht-Straße 24-25, 14476 Potsdam, Germany
Abstract
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 Bou-Rabee, Eberle and Zimmer (2020).
Publisher
Oxford University Press (OUP)
Subject
Applied Mathematics,Computational Mathematics,General Mathematics
Reference30 articles.
1. Optimal tuning of the hybrid monte carlo algorithm;Beskos;Bernoulli,2013
2. Hybrid Monte Carlo on Hilbert spaces;Beskos;Stochastic Process. Appl.,2011
3. Coupling and convergence for Hamiltonian Monte Carlo;Bou-Rabee,2018
4. Randomized Hamiltonian Monte Carlo;Bou-Rabee;Ann. Appl. Probab.,2017
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献