dynesty: a dynamic nested sampling package for estimating Bayesian posteriors and evidences

TLDR

Dynamic nested sampling combines the posterior‑focused efficiency of MCMC with nested sampling’s ability to estimate evidences and handle multimodal distributions. This work introduces dynesty, a public Python package that implements dynamic nested sampling to estimate Bayesian posteriors and evidences. Dynesty adaptively allocates samples based on posterior structure, and its performance is demonstrated on toy problems and several astronomical applications, with detailed statistical results provided in the appendix. In astronomical applications, dynesty achieves substantial sampling‑efficiency gains over popular MCMC approaches.

Abstract

ABSTRACT We present dynesty, a public, open-source, python package to estimate Bayesian posteriors and evidences (marginal likelihoods) using the dynamic nested sampling methods developed by Higson et al. By adaptively allocating samples based on posterior structure, dynamic nested sampling has the benefits of Markov chain Monte Carlo (MCMC) algorithms that focus exclusively on posterior estimation while retaining nested sampling’s ability to estimate evidences and sample from complex, multimodal distributions. We provide an overview of nested sampling, its extension to dynamic nested sampling, the algorithmic challenges involved, and the various approaches taken to solve them in this and previous work. We then examine dynesty’s performance on a variety of toy problems along with several astronomical applications. We find in particular problems dynesty can provide substantial improvements in sampling efficiency compared to popular MCMC approaches in the astronomical literature. More detailed statistical results related to nested sampling are also included in the appendix.