Interacting Particle Markov Chain Monte Carlo
Computation
2017-04-13 v3 Machine Learning
Abstract
We introduce interacting particle Markov chain Monte Carlo (iPMCMC), a PMCMC method based on an interacting pool of standard and conditional sequential Monte Carlo samplers. Like related methods, iPMCMC is a Markov chain Monte Carlo sampler on an extended space. We present empirical results that show significant improvements in mixing rates relative to both non-interacting PMCMC samplers, and a single PMCMC sampler with an equivalent memory and computational budget. An additional advantage of the iPMCMC method is that it is suitable for distributed and multi-core architectures.
Cite
@article{arxiv.1602.05128,
title = {Interacting Particle Markov Chain Monte Carlo},
author = {Tom Rainforth and Christian A. Naesseth and Fredrik Lindsten and Brooks Paige and Jan-Willem van de Meent and Arnaud Doucet and Frank Wood},
journal= {arXiv preprint arXiv:1602.05128},
year = {2017}
}