Adaptive Tuning of Hamiltonian Monte Carlo Within Sequential Monte Carlo - Centre de Recherche en Économie et Statistique
Article Dans Une Revue Bayesian Analysis Année : 2021

Adaptive Tuning of Hamiltonian Monte Carlo Within Sequential Monte Carlo

Alexander Buchholz
  • Fonction : Auteur
Pierre Jacob
  • Fonction : Auteur

Résumé

Sequential Monte Carlo (SMC) samplers are an alternative to MCMC for Bayesian computation. However, their performance depends strongly on the Markov kernels used to rejuvenate particles. We discuss how to calibrate automatically (using the current particles) Hamiltonian Monte Carlo kernels within SMC. To do so, we build upon the adaptive SMC approach of Fearnhead and Taylor (2013), and we also suggest alternative methods. We illustrate the advantages of using HMC kernels within an SMC sampler via an extensive numerical study.
Fichier principal
Vignette du fichier
20-BA1222.pdf (713.21 Ko) Télécharger le fichier
Origine Publication financée par une institution

Dates et versions

hal-04793468 , version 1 (06-01-2025)

Identifiants

Citer

Alexander Buchholz, Nicolas Chopin, Pierre Jacob. Adaptive Tuning of Hamiltonian Monte Carlo Within Sequential Monte Carlo. Bayesian Analysis, 2021, 16 (3), ⟨10.1214/20-BA1222⟩. ⟨hal-04793468⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More