zeus: A Python implementation of Ensemble Slice Sampling for efficient Bayesian parameter inference

TL;DR

zeus is a Python library implementing Ensemble Slice Sampling, an MCMC method optimized for high-dimensional, correlated, and multimodal Bayesian inference tasks common in astronomy and cosmology, with minimal tuning and high scalability.

Contribution

The paper introduces zeus, a Python implementation of Ensemble Slice Sampling that improves efficiency, scalability, and ease of use for complex Bayesian inference problems.

Findings

zeus outperforms emcee by factors of 9 and 29 in specific applications.

It requires minimal hyper-parameter tuning.

It scales efficiently to thousands of CPUs.

Abstract

We introduce zeus, a well-tested Python implementation of the Ensemble Slice Sampling (ESS) method for Bayesian parameter inference. ESS is a novel Markov chain Monte Carlo (MCMC) algorithm specifically designed to tackle the computational challenges posed by modern astronomical and cosmological analyses. In particular, the method requires only minimal hand--tuning of 1-2 hyper-parameters that are often trivial to set; its performance is insensitive to linear correlations and it can scale up to 1000s of CPUs without any extra effort. Furthermore, its locally adaptive nature allows to sample efficiently even when strong non-linear correlations are present. Lastly, the method achieves a high performance even in strongly multimodal distributions in high dimensions. Compared to emcee, a popular MCMC sampler, zeus performs 9 and 29 times better in a cosmological and an exoplanet application respectively.