Machine-learning cosmology from void properties

TL;DR

This paper demonstrates that machine learning models can effectively extract cosmological information from cosmic void properties, achieving precise parameter constraints without spatial data, using large void catalogs.

Contribution

The study introduces machine learning approaches to infer cosmological parameters from void features, achieving high accuracy without relying on spatial information.

Findings

Neural networks constrain _m, _8, and n_s with 10%, 4%, and 3% errors.

Models perform likelihood-free inference from void property histograms and catalogs.

Results highlight machine learning's potential in void-based cosmological analysis.

Abstract

Cosmic voids are the largest and most underdense structures in the Universe. Their properties have been shown to encode precious information about the laws and constituents of the Universe. We show that machine learning techniques can unlock the information in void features for cosmological parameter inference. We rely on thousands of void catalogs from the GIGANTES dataset, where every catalog contains an average of 11,000 voids from a volume of $1~(h^{-1}{\rm Gpc})^3$. We focus on three properties of cosmic voids: ellipticity, density contrast, and radius. We train 1) fully connected neural networks on histograms from individual void properties and 2) deep sets from void catalogs, to perform likelihood-free inference on the value of cosmological parameters. We find that our best models are able to constrain the value of $\Omega_{\rm m}$, $\sigma_8$, and $n_s$ with mean relative errors of $10\%$, $4\%$, and $3\%$, respectively, without using any spatial information from the void catalogs. Our results provide an illustration for the use of machine learning to constrain cosmology with voids.