cosmoabc: Likelihood-free inference via Population Monte Carlo Approximate Bayesian Computation

Abstract

Approximate Bayesian Computation (ABC) enables parameter inference for complex physical systems in cases where the true likelihood function is unknown, unavailable, or computationally too expensive. It relies on the forward simulation of mock data and comparison between observed and synthetic catalogues. Here we present cosmoabc, a Python ABC sampler featuring a Population Monte Carlo (PMC) variation of the original ABC algorithm, which uses an adaptive importance sampling scheme. The code is very flexible and can be easily coupled to an external simulator, while allowing to incorporate arbitrary distance and prior functions. As an example of practical application, we coupled cosmoabc with the numcosmo library and demonstrate how it can be used to estimate posterior probability distributions over cosmological parameters based on measurements of galaxy clusters number counts without computing the likelihood function. cosmoabc is published under the GPLv3 license on PyPI and GitHub and documentation is available at http://goo.gl/SmB8EX

Add missing variable to algorithm 1 description. To see all frames in figure 4 download the pdf and open with Adobe Reader (or equivalent) and use the controls bellow the plot

References in corpus (5)

• Binary interaction dominates the evolution of massive stars
• Cosmological Constraints from the SDSS Luminous Red Galaxies
• Galaxy Clusters Discovered via the Sunyaev-Zel'dovich Effect in the 2500-square-degree SPT-SZ survey
• Approximate Bayesian Computation for Forward Modeling in Cosmology
• The AstraLux Multiplicity Survey: Extension to Late M-dwarfs

Cited by in corpus (53)

• Machine learning and the physical sciences
• COLDz: Shape of the CO Luminosity Function at High Redshift and the Cold Gas History of the Universe
• Massive optimal data compression and density estimation for scalable, likelihood-free inference in cosmology
• Searching the Entirety of Kepler Data. II. Occurrence Rate Estimates for FGK Stars
• Likelihood-free inference with neural compression of DES SV weak lensing map statistics
• Nuisance hardened data compression for fast likelihood-free inference
• Variability Timescale and Spectral Index of Sgr A* in the Near Infrared: Approximate Bayesian Computation Analysis of the Variability of the Closest Supermassive Black Hole
• Automatic physical inference with information maximising neural networks
• Generalized massive optimal data compression
• Bayesian optimisation for likelihood-free cosmological inference
• Improving the Accuracy of Planet Occurrence Rates from Kepler using Approximate Bayesian Computation
• A new model to predict weak-lensing peak counts II. Parameter constraint strategies
• Simulation-Based Inference of Reionization Parameters From 3D Tomographic 21 cm Lightcone Images
• Comparison of statistical sampling methods with ScannerBit, the GAMBIT scanning module
• astroABC: An Approximate Bayesian Computation Sequential Monte Carlo sampler for cosmological parameter estimation
• Mocking the Weak Lensing universe: the LensTools python computing package
• Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimation
• A New Method to Measure the Post-Reionization Ionizing Background from the Joint Distribution of Lyman-$\alpha$ and Lyman-$\beta$ Forest Transmission
• Approximate Bayesian Computation in Large Scale Structure: constraining the galaxy-halo connection
• Cosmological constraints with weak lensing peak counts and second-order statistics in a large-field survey
• $\mathtt{bajes}$: Bayesian inference of multimessenger astrophysical data, methods and application to gravitational-waves
• Star Formation Quenching Timescale of Central Galaxies in a Hierarchical Universe
• Towards a model-independent reconstruction approach for late-time Hubble data
• The multiplicity distribution of Kepler's exoplanets
• Cosmic Shear: Inference from Forward Models
• Cosmological parameter estimation via iterative emulation of likelihoods
• Machine Learning for Observational Cosmology
• Dark energy by natural evolution: Constraining dark energy using Approximate Bayesian Computation
• Accelerating Approximate Bayesian Computation with Quantile Regression: Application to Cosmological Redshift Distributions
• Kernel Selection for Gaussian Process in Cosmology: with Approximate Bayesian Computation Rejection and Nested Sampling
• Benchmarking Simulation-Based Inference
• 21st Century Statistical and Computational Challenges in Astrophysics
• Primordial power spectrum and cosmology from black-box galaxy surveys
• Inferring the photometric and size evolution of galaxies from image simulations
• A simulation-based inference pipeline for cosmic shear with the Kilo-Degree Survey
• CoLFI: Cosmological Likelihood-free Inference with Neural Density Estimators
• Hybrid analytic and machine-learned baryonic property insertion into galactic dark matter haloes
• Cosmological Parameter Estimation and Inference using Deep Summaries
• Machine Learning Accelerated Likelihood-Free Event Reconstruction in Dark Matter Direct Detection
• Likelihood-free Forward Modeling for Cluster Weak Lensing and Cosmology
• A Preferential Attachment Model for the Stellar Initial Mass Function
• Hubble constant by natural selection: Evolution chips in the Hubble tension
• Deep Learning and genetic algorithms for cosmological Bayesian inference speed-up
• On the Asymptotic Efficiency of Approximate Bayesian Computation Estimators
• Combining Transit and RV: A Synthesized Population Model
• Simulation-based marginal likelihood for cluster strong lensing cosmology
• Gaussbock: Fast parallel-iterative cosmological parameter estimation with Bayesian nonparametrics
• Boosting MonteCarlo sampling with a non-Gaussian fit
• Minimum-entropy constraints on galactic potentials
• Trans-Neptunian Space and the Post-Pluto Paradigm
• Diagnosing Systematic Effects Using the Inferred Initial Power Spectrum
• IQ Collaboratory III: The Empirical Dust Attenuation Framework -- Taking Hydrodynamical Simulations with a Grain of Dust
• On the Connection between Field-Level Inference and $n$-point Correlation Functions