Couplings for Andersen Dynamics
Probability
2022-05-17 v1 Chemical Physics
Computational Physics
Machine Learning
Abstract
Andersen dynamics is a standard method for molecular simulations, and a precursor of the Hamiltonian Monte Carlo algorithm used in MCMC inference. The stochastic process corresponding to Andersen dynamics is a PDMP (piecewise deterministic Markov process) that iterates between Hamiltonian flows and velocity randomizations of randomly selected particles. Both from the viewpoint of molecular dynamics and MCMC inference, a basic question is to understand the convergence to equilibrium of this PDMP particularly in high dimension. Here we present couplings to obtain sharp convergence bounds in the Wasserstein sense that do not require global convexity of the underlying potential energy.
Cite
@article{arxiv.2009.14239,
title = {Couplings for Andersen Dynamics},
author = {Nawaf Bou-Rabee and Andreas Eberle},
journal= {arXiv preprint arXiv:2009.14239},
year = {2022}
}
Comments
36 pages, 8 figures