Machine-learning Cosmology from Void Properties

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 data set, where every catalog contains an average of 11,000 voids from a volume of 1 h − 1 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 Ω m , σ 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.

Cosmology from One Galaxy in a Void?

“…Voids are sensitive probes to extract cosmological information (e.g., Park & Lee 2007;Biswas et al 2010;Lavaux & Wandelt 2010, 2012Pisani et al 2015aPisani et al , 2019Hamaus et al 2016;Verza et al 2019;Kreisch et al 2022;Stopyra et al 2021;Contarini et al 2023Contarini et al , 2022Pelliciari et al 2023;Schuster et al 2023;Wang et al 2023): for instance the voidgalaxy cross-correlation function and the void size function already provide tight constraints on Ω m (Hamaus et al 2020;Contarini et al 2022). Since voids are gold mines of cosmological information (Pisani et al 2019;Moresco et al 2022), it is interesting to ask whether galaxies inside voids bear a stronger constraining power from a cosmology perspective.…”

Can We Constrain Warm Dark Matter Masses with Individual Galaxies?

“…If individual galaxies cannot be used to infer WDM masses, it may still be possible, and expected, that sets of galaxies can. It would be interesting to quantify how much information can be extracted from an ensemble of them, e.g., using deep sets (Wang et al 2023) or graph neural networks (Villanueva-Domingo et al 2021Shao et al 2022;de Santi et al 2023;Nguyen et al 2023).…”