MCMC Using Ensembles of States for Problems with Fast and Slow Variables such as Gaussian Process Regression

Abstract

I introduce a Markov chain Monte Carlo (MCMC) scheme in which sampling from a distribution with density pi(x) is done using updates operating on an "ensemble" of states. The current state x is first stochastically mapped to an ensemble, x^{(1)},...,x^{(K)}. This ensemble is then updated using MCMC updates that leave invariant a suitable ensemble density, rho(x^{(1)},...,x^{(K)}), defined in terms of pi(x^{(i)}) for i=1,...,K. Finally a single state is stochastically selected from the ensemble after these updates. Such ensemble MCMC updates can be useful when characteristics of pi and the ensemble permit pi(x^{(i)}) for all i in {1,...,K}, to be computed in less than K times the amount of computation time needed to compute pi(x) for a single x. One common situation of this type is when changes to some "fast" variables allow for quick re-computation of the density, whereas changes to other "slow" variables do not. Gaussian process regression models are an example of this sort of problem, with an overall scaling factor for covariances and the noise variance being fast variables. I show that ensemble MCMC for Gaussian process regression models can indeed substantially improve sampling performance. Finally, I discuss other possible applications of ensemble MCMC, and its relationship to the "multiple-try Metropolis" method of Liu, Liang, and Wong and the "multiset sampler" of Leman, Chen, and Lavine.

References in corpus (2)

• Cosmological parameters from CMB and other data: a Monte-Carlo approach
• Taking Bigger Metropolis Steps by Dragging Fast Variables

Cited by in corpus (12)

• Layered Adaptive Importance Sampling
• A Review of Multiple Try MCMC algorithms for Signal Processing
• Orthogonal parallel MCMC methods for sampling and optimization
• Computing Bayes: From Then 'Til Now'
• On embedded hidden Markov models and particle Markov chain Monte Carlo methods
• Metropolis-Hastings with Averaged Acceptance Ratios
• MCMC with Strings and Branes: The Suburban Algorithm
• MCMC with Strings and Branes: The Suburban Algorithm (Extended Version)
• Replica Conditional Sequential Monte Carlo
• Fast Markov Chain Monte Carlo Algorithms via Lie Groups
• Quantum Speedups for Multiproposal MCMC
• Fast matrix computations for functional additive models