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

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.

arXiv comment15 pages, 17 figures, 2 tables, published in MNRAS; Code available at https://github.com/minaskar/zeus

References in corpus (19)

• Scikit-learn: Machine Learning in Python
• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• emcee: The MCMC Hammer
• The NumPy array: a structure for efficient numerical computation
• SDSS-III: Massive Spectroscopic Surveys of the Distant Universe, the Milky Way Galaxy, and Extra-Solar Planetary Systems
• The Baryon Oscillation Spectroscopic Survey of SDSS-III
• The DESI Experiment Part I: Science,Targeting, and Survey Design
• A Conceptual Introduction to Hamiltonian Monte Carlo
• RadVel: The Radial Velocity Modeling Toolkit
• CosmoSIS: modular cosmological parameter estimation
• emcee v3: A Python ensemble sampling toolkit for affine-invariant MCMC
• The clustering of galaxies in the completed SDSS-III Baryon Oscillation Spectroscopic Survey: Baryon Acoustic Oscillations in Fourier-space
• Ensemble Slice Sampling: Parallel, black-box and gradient-free inference for correlated & multimodal distributions
• A Conceptual Introduction to Markov Chain Monte Carlo Methods
• Two Transiting Low Density Sub-Saturns from K2
• Impact of Relativistic Effects on the Primordial Non-Gaussianity Signature in the Large-Scale Clustering of Quasars
• The effect of finite halo size on the clustering of neutral hydrogen
• Accelerating MCMC Algorithms
• Testing and Emulating Modified Gravity on Cosmological Scales

Cited by in corpus (40)

• The CosmoVerse White Paper: Addressing observational tensions in cosmology with systematics and fundamental physics
• Hyper Suprime-Cam Year 3 Results: Cosmology from Cosmic Shear Power Spectra
• pyaneti II: A multidimensional Gaussian process approach to analysing spectroscopic time-series
• Unified galaxy power spectrum measurements from 6dFGS, BOSS, and eBOSS
• Accelerating astronomical and cosmological inference with Preconditioned Monte Carlo
• Baryon Acoustic Oscillation Theory and Modelling Systematics for the DESI 2024 results
• Robust sampling for weak lensing and clustering analyses with the Dark Energy Survey
• Gravitational Redshift Constraints on the Effective Theory of Interacting Dark Energy
• Detecting the power spectrum turnover with HI intensity mapping
• The DESI PRObabilistic Value-Added Bright Galaxy Survey (PROVABGS) Mock Challenge
• LINNA: Likelihood Inference Neural Network Accelerator
• Calibrating cosmological simulations with implicit likelihood inference using galaxy growth observables
• $\text{matryoshka}$ II: Accelerating Effective Field Theory Analyses of the Galaxy Power Spectrum
• Measuring line-of-sight shear with Einstein rings: a proof of concept
• Modelling stellar activity with Gaussian process regression networks
• NGTS clusters survey -- III: A low-mass eclipsing binary in the Blanco 1 open cluster spanning the fully convective boundary
• Measurement of the matter-radiation equality scale using the extended Baryon Oscillation Spectroscopic Survey Quasar Sample
• A GPU-accelerated semi-coherent hierarchical search for stellar-mass binary inspiral signals in LISA
• The SRG/eROSITA all-sky survey. X-ray emission from the warm-hot phase gas in long cosmic filaments
• Interferometric HI intensity mapping: perturbation theory predictions and foreground removal effects
• Neural Stellar Population Synthesis Emulator for the DESI PROVABGS
• pop-cosmos: Scaleable inference of galaxy properties and redshifts with a data-driven population model
• A comparison of Bayesian sampling algorithms for high-dimensional particle physics and cosmology applications
• Constraining Exponential f(Q) Gravity with Cosmic Chronometers and Supernovae: A Data-Driven Analysis
• A measurement of the Integrated Sachs-Wolfe Effect with the Rapid ASKAP Continuum Survey
• Angular systematics-free cosmological analysis of galaxy clustering in configuration space
• Weak lensing of strong lensing: beyond the tidal regime
• GausSN: Bayesian Time-Delay Estimation for Strongly Lensed Supernovae
• Host group degeneracy in gravitational lensing time delay determination of $H_0$
• Reconstructing the epoch of reionisation with Planck PR4
• Deciphering Baryonic Feedback from ACT tSZ Galaxy Clusters
• Cosmological implications of the Gaia Milky Way declining rotation curve
• Searching for stellar-origin binary black holes in LISA Data Challenge 1b: Yorsh
• A comparison of shrinkage estimators of the cosmological precision matrix
• A new consistency test for $\Lambda$CDM cosmology using galaxy surveys
• Reconstruction of Tsallis Holographic Dark Energy via Modified Non-Metric Gravity: An $f(Q,C)$ Approach
• Cosmological Dynamics of Exponential Quintessence Constrained by BAO, Cosmic Chronometers, and DES-SN5YR/Pantheon+ Data
• Identification of low redshift groups and clusters of galaxies in the X-CLASS survey and the X-ray luminosity-temperature relation
• A flexible method for estimating luminosity functions via Kernel Density Estimation -- II. Generalization and Python implementation
• APES: Approximate Posterior Ensemble Sampler