Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
173 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Concentration inequalities and performance guarantees for hypocoercive MCMC samplers (1907.11973v1)

Published 27 Jul 2019 in math.PR

Abstract: In this paper we provide performance guarantees for hypocoercive non-reversible MCMC samplers $X_t$ with invariant measure $\mu*$ 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 $\frac{1}{T} \int_0T f(X_t)\, dt$. As a consequence we provide performance guarantees: (a) explicit non-asymptotic confidence intervals for $\int f d\mu*$ 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 $\int f d\mu*$ 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)

Summary

We haven't generated a summary for this paper yet.