Adaptive Tuning Of Hamiltonian Monte Carlo Within Sequential Monte Carlo

TL;DR

This paper introduces an adaptive method for calibrating Hamiltonian Monte Carlo kernels within Sequential Monte Carlo samplers, enhancing Bayesian computation efficiency.

Contribution

It proposes an automatic calibration technique for HMC kernels within SMC, building on adaptive SMC methods and offering alternative approaches.

Findings

HMC kernels improve SMC performance in Bayesian tasks

Adaptive calibration enhances sampling efficiency

Numerical studies demonstrate advantages over traditional methods

Abstract

Sequential Monte Carlo (SMC) samplers form an attractive 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.