Stability of Conditional Sequential Monte Carlo

TL;DR

This paper analyzes the stability and mixing properties of the conditional Sequential Monte Carlo (cSMC) method within particle Gibbs samplers, providing bounds and a CLT to ensure reliable sampling in complex models.

Contribution

It introduces a novel interpretation of cSMC as a perturbed SMC, derives uniform ergodicity bounds, and proves a central limit theorem for cSMC, advancing theoretical understanding.

Findings

cSMC mixing rate can be maintained constant with linearly increasing particles

Derived a bound for the distance between cSMC samples and the target distribution

Proved a central limit theorem for the cSMC algorithm

Abstract

The particle Gibbs (PG) sampler is a Markov Chain Monte Carlo (MCMC) algorithm, which uses an interacting particle system to perform the Gibbs steps. Each Gibbs step consists of simulating a particle system conditioned on one particle path. It relies on a conditional Sequential Monte Carlo (cSMC) method to create the particle system. We propose a novel interpretation of the cSMC algorithm as a perturbed Sequential Monte Carlo (SMC) method and apply telescopic decompositions developed for the analysis of SMC algorithms \cite{delmoral2004} to derive a bound for the distance between the expected sampled path from cSMC and the target distribution of the MCMC algorithm. This can be used to get a uniform ergodicity result. In particular, we can show that the mixing rate of cSMC can be kept constant by increasing the number of particles linearly with the number of observations. Based on our decomposition, we also prove a central limit theorem for the cSMC Algorithm, which cannot be done using the approaches in \cite{Andrieu2013} and \cite{Lindsten2014}.