A copula based approach to adaptive sampling

TL;DR

This paper introduces a copula-based adaptive sampling method for Bayesian inference, demonstrating improved efficiency and acceptance rates over traditional proposals through comparisons on realistic models and data.

Contribution

It presents a novel copula-based proposal density combined with antithetic sampling, outperforming existing adaptive proposals in efficiency and acceptance rates.

Findings

Copula-based proposals outperform mixture of normals and random walk in efficiency.

Antithetic sampling enhances proposal efficiency.

Copula proposals achieve higher acceptance rates and lower inefficiencies.

Abstract

Our article is concerned with adaptive sampling schemes for Bayesian inference that update the proposal densities using previous iterates. We introduce a copula based proposal density which is made more efficient by combining it with antithetic variable sampling. We compare the copula based proposal to an adaptive proposal density based on a multivariate mixture of normals and an adaptive random walk Metropolis proposal. We also introduce a refinement of the random walk proposal which performs better for multimodal target distributions. We compare the sampling schemes using challenging but realistic models and priors applied to real data examples. The results show that for the examples studied, the adaptive independent \MH{} proposals are much more efficient than the adaptive random walk proposals and that in general the copula based proposal has the best acceptance rates and lowest inefficiencies.