[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118876-en":3,"doc-seo-118876-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118876,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Machine-learning cosmology from void properties","Cosmic voids are the Universe’s largest underdense structures, and their features carry information about the laws and constituents shaping cosmic evolution. This work demonstrates that machine learning can extract void-feature information for cosmological parameter inference. Using thousands of void catalogs from the GIGANTES dataset, the study trains neural networks on histogrammed void properties and deep sets on full catalogs for likelihood-free inference, constraining Ωm, σ8, and ns with small mean relative errors.","arXiv :2212 .06860v2 [ astro-ph .CO] 7 Oct 2023  \nDraft version October 10, 2023  \nTypeset using LATEX twocolumn style in AASTeX631  \nMachine-learning cosmology from void properties  \nBonny Y. Wang (汪玥)  ,1, 2 Alice Pisani  ,1, 2, 3 Francisco Villaescusa-Navarro  ,2, 3 and  \nBenjamin D. Wandelt 2, 4  \n1 The Cooper Union, 30 Cooper Sq, New York, NY 10003 USA  \n2 Center for Computational Astrophysics, Flatiron Institute, 162 5th Avenue, New York, NY 10010 USA  \n3 Department of Astrophysical Sciences, Princeton University, 4 Ivy Lane, Princeton, NJ 08544 USA  \n4 Sorbonne Universit´e, CNRS, UMR 7095, Institut d’Astrophysique de Paris, 98 bis bd Arago, 75014 Paris, France  \nABSTRACT  \nCosmic 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−1Gpc)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 likelihoodfree inference on the value of cosmological parameters. We find that our best models are able to constrain the value of Ωm , σ8 , and ns 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.  \nKeywords: cosmology, large-scale structure, cosmic voids, machine learning  \n1. INTRODUCTION  \nCosmic voids, the underdense regions in the galaxy distribution, are dominated by dark energy and account for most of the volume of the Universe (Gregory & Thompson 1978; J˜oeveer et al. 1978; Kirshner et al. 1981; Zeldovich et al. 1982; van de Weygaert & van Kampen 1993; Bond et al. 1996; Tikhonov & Karachentsev 2006) . Thanks to their underdense feature, voids are particularly sensitive to cosmological information (Park & Lee 2007; Lavaux & Wandelt 2010; Bos et al. 2012; Lavaux & Wandelt 2012; Pisani et al. 2015; Hamauset al. 2016; Mao et al. 2017; Pisani et al. 2019; Sahl´en 2019; Verza et al. 2019; Ronconi et al. 2019; Chan et al. 2019; Bayer et al. 2021; Kreisch et al. 2021; Wilson & Bean 2021; Contarini et al. 2022c; Pelliciari et al. 2022; Contarini et al. 2022a) . Until recently, void numbers were relatively low given the fact that voids are large regions and that the volume of surveys was relatively  \nCorresponding author: Bonny Y. Wang  \n[ywang@flatironinstitute.org](ywang@flatironinstitute.org)  \nsmall. Nowadays, large-scale surveys are expected to enable big data approaches for studying voids, revealing their relationship to cosmological models in all its strength. Upcoming surveys will provide of the order of 105 voids each, gaining more than an order of magnitude in void numbers (Pisani et al. 2019; Moresco et al. 2022) . Along with the large increase in available data from current and upcoming surveys, void data from simulations is also dramatically increasing (see e.g. the extensive GIGANTES set of void catalogs in Kreisch et al. (2021))—enabling the usage of machine learning to analyze voidsand find correlations with the value of cosmological parameters.  \nTo extract cosmological information from voids, robust theoretical predictions are necessary for each of the different void statistics; examples include the void size function, providing the void number density as a function of void radii, and the void-galaxy cross-correlation function, corresponding to the density profile of voids (see e.g. Hamaus et al. 2016; Verza et al. 2019; Pisaniet al. 2019; Hamaus et al. 2020; Contarini et al. 2022c) . ","cbCaihB6RY59HdRU","https://ap.wps.com/l/cbCaihB6RY59HdRU","pdf",2012015,1,13,"English","en",105,"# Introduction\n## Why void properties contain cosmological information\n## Limitations of current void modeling and motivation for machine learning","[{\"question\":\"What problem does the study address about cosmic voids?\",\"answer\":\"It addresses how to unlock cosmological information encoded in cosmic void features beyond traditional void statistics, using machine learning for parameter inference.\"},{\"question\":\"Which void properties are used for the machine learning models?\",\"answer\":\"The models focus on ellipticity, density contrast, and radius of cosmic voids.\"},{\"question\":\"How are cosmological parameters inferred in this approach?\",\"answer\":\"The study performs likelihood-free inference by training neural networks on void-property histograms and deep sets on void catalogs, then predicting cosmological parameters.\"}]","Machine-learning cosmology from void properties | PDF",1785720738,33,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-cosmology-from-void-properties","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-cosmology-from-void-properties/118876/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study address about cosmic voids?","Question",{"text":75,"@type":76},"It addresses how to unlock cosmological information encoded in cosmic void features beyond traditional void statistics, using machine learning for parameter inference.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which void properties are used for the machine learning models?",{"text":80,"@type":76},"The models focus on ellipticity, density contrast, and radius of cosmic voids.",{"name":82,"@type":73,"acceptedAnswer":83},"How are cosmological parameters inferred in this approach?",{"text":84,"@type":76},"The study performs likelihood-free inference by training neural networks on void-property histograms and deep sets on void catalogs, then predicting cosmological parameters.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]