Concentration inequalities and performance guarantees for hypocoercive MCMC samplers

arXiv1907.11973MaRDI QIDQ6322786FDOQ6322786

Authors: Jeremiah Birrell, Luc Rey-Bellet 

Publication date: 27 July 2019

Abstract: In this paper we provide performance guarantees for hypocoercive non-reversible MCMC samplers $X_t$ with invariant measure $m{u}^{*}$ and our results apply in particular to the Langevin equation, Hamiltonian Monte-Carlo, and the bouncy particle and zig-zag samplers. Specifically, we establish a concentration inequality of Bernstein type for ergodic averages $frac1Tin{t}_0^{T}f(X_t),dt$. As a consequence we provide performance guarantees: (a) explicit non-asymptotic confidence intervals for $intfdm{u}^{\ast }$ when using a finite time ergodic average with given initial condition $mu$ and (b) uncertainty quantification bounds, expressed in terms of relative entropy rate, on the bias of $intfdm{u}^{\ast }$ when using an alternative or approximate processes $widetilde{X}_t$. (Results in (b) generalize recent results (arXiv:1812.05174) from the authors for coercive dynamics.) The concentration inequality is proved by combining the approach via Feynmann-Kac semigroups first noted by Wu with the hypocoercive estimates of Dolbeault, Mouhot and Schmeiser (arXiv:1005.1495) developed for the Langevin equation and recently generalized to partially deterministic Markov processes by Andrieu et al. (arXiv:1808.08592)

This page was built for publication: Concentration inequalities and performance guarantees for hypocoercive MCMC samplers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6322786)