betaFeedback

WorksMathematics

High-probability Uniform Mixing via Dobrushin Contraction and Accelerated Hamiltonian Monte Carlo

Abstract

Hamiltonian Monte Carlo, since its invention and subsequent rise to widespread use, has been motivated by its ability to accelerate convergence to equilibrium compared to diffusive methods, both in terms of dependence on condition number and dimension. In the present work, we establish this acceleration simultaneously in both aspects for critically damped Metropolis-adjusted kinetic Langevin with persistent uniforms. More precisely, for target measures μ(dx)∝e−U(x)dxμ(dx)\propto e^{-U(x)}dx with mm-strongly convex, LL-gradient Lipschitz, and LHL_H-Frobenius Hessian Lipschitz potentials, we show that the method mixes to ε\varepsilon-accuracy in total variation using O((κ1/2+LH1/2m−3/4) d1/4)\mathcal O\bigl((κ^{1/2}+L_H^{1/2}m^{-3/4})\,d^{1/4}\bigr) gradient evaluations up to logarithmic factors, both uniformly over starting points in domains of high equilibrium probability and from warm starts. The proof incorporates ideas from previous studies by Bou-Rabee and Chen et al. that show either aspect of acceleration separately, into novel coupling technology. This new coupling technology for general Markov chains extends earlier frameworks aimed at capturing fast local equilibration in the presence of slow global mixing. Specifically, via a weak-(1,1)(1,1) maximal inequality that follows from Hopf's maximal ergodic theorem, we uncover a stability mechanism in high-probability domains with respect to equilibrium. This enables straightforward localization to naturally arising domains of fast local mixing, and seamlessly fits broad local frameworks via Dobrushin contraction, Wasserstein contraction and local Harris' theorems. We develop the Dobrushin formulation.

Paper details

vlnc:W_k9aync9g
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
arXiv nonexclusive license
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Mathematics

Not recorded for this paper

View statement
Looking for related papers…