Second order quantitative bounds for unadjusted generalized Hamiltonian Monte Carlo - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Second order quantitative bounds for unadjusted generalized Hamiltonian Monte Carlo

Résumé

This paper provides a convergence analysis for generalized Hamiltonian Monte Carlo samplers, a family of Markov Chain Monte Carlo methods based on leapfrog integration of Hamiltonian dynamics and kinetic Langevin diffusion, that encompasses the unadjusted Hamiltonian Monte Carlo method. Assuming that the target distribution $\pi$ satisfies a log-Sobolev inequality and mild conditions on the corresponding potential function, we establish quantitative bounds on the relative entropy of the iterates defined by the algorithm, with respect to $\pi$. Our approach is based on a perturbative and discrete version of the modified entropy method developed to establish hypocoercivity for the continuous-time kinetic Langevin process. As a corollary of our main result, we are able to derive complexity bounds for the class of algorithms at hand. In particular, we show that the total number of iterations to achieve a target accuracy $\varepsilon >0$ is of order $d/\varepsilon^{1/4}$, where $d$ is the dimension of the problem. This result can be further improved in the case of weakly interacting mean field potentials, for which we find a total number of iterations of order $(d/\varepsilon)^{1/4}$.

Dates et versions

hal-04574037 , version 1 (13-05-2024)

Identifiants

Citer

Evan Camrud, Alain Oliviero Durmus, Pierre Monmarché, Gabriel Stoltz. Second order quantitative bounds for unadjusted generalized Hamiltonian Monte Carlo. 2024. ⟨hal-04574037⟩
36 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More