Ensemble Transport Adaptive Importance Sampling

TL;DR

This paper introduces ETAIS, an ensemble transport adaptive importance sampling method that improves sampling efficiency over traditional MCMC, especially for complex, multimodal, and computationally expensive problems, with potential for parallelization.

Contribution

The paper presents ETAIS, a novel ensemble-based importance sampling algorithm with a new resampling strategy and parameter tuning methods, outperforming MCMC in various challenging scenarios.

Findings

ETAIS outperforms MCMC with similar proposals in low dimensions.

Better than linear convergence improvements with ensemble size.

Significant speed-ups for complex, multimodal, and expensive likelihood problems.

Abstract

Markov chain Monte Carlo methods are a powerful and commonly used family of numerical methods for sampling from complex probability distributions. As applications of these methods increase in size and complexity, the need for efficient methods increases. In this paper, we present a particle ensemble algorithm. At each iteration, an importance sampling proposal distribution is formed using an ensemble of particles. A stratified sample is taken from this distribution and weighted under the posterior, a state-of-the-art ensemble transport resampling method is then used to create an evenly weighted sample ready for the next iteration. We demonstrate that this ensemble transport adaptive importance sampling (ETAIS) method outperforms MCMC methods with equivalent proposal distributions for low dimensional problems, and in fact shows better than linear improvements in convergence rates with respect to the number of ensemble members. We also introduce a new resampling strategy, multinomial transformation (MT), which while not as accurate as the ensemble transport resampler, is substantially less costly for large ensemble sizes, and can then be used in conjunction with ETAIS for complex problems. We also focus on how algorithmic parameters regarding the mixture proposal can be quickly tuned to optimise performance. In particular, we demonstrate this methodology's superior sampling for multimodal problems, such as those arising from inference for mixture models, and for problems with expensive likelihoods requiring the solution of a differential equation, for which speed-ups of orders of magnitude are demonstrated. Likelihood evaluations of the ensemble could be computed in a distributed manner, suggesting that this methodology is a good candidate for parallel Bayesian computations.