{"id":"https://openalex.org/W4384075754","doi":"https://doi.org/10.48550/arxiv.2307.04201","title":"Bayesian estimation of the Kullback-Leibler divergence for categorical sytems using mixtures of Dirichlet priors","display_name":"Bayesian estimation of the Kullback-Leibler divergence for categorical sytems using mixtures of Dirichlet priors","publication_year":2023,"publication_date":"2023-07-09","ids":{"openalex":"https://openalex.org/W4384075754","doi":"https://doi.org/10.48550/arxiv.2307.04201"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2307.04201","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.04201","pdf_url":"https://arxiv.org/pdf/2307.04201","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2307.04201","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003388066","display_name":"Francesco Camaglia","orcid":"https://orcid.org/0000-0003-4810-2631","observed_orcids":["https://orcid.org/0000-0003-4810-2631"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I4210129651","display_name":"Laboratoire de Physique de l'Ecole Normale Sup\u00e9rieure","ror":"https://ror.org/03a26mh11","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I2746051580","https://openalex.org/I2800004676","https://openalex.org/I29607241","https://openalex.org/I39804081","https://openalex.org/I4210129651"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Camaglia, Francesco","raw_affiliation_strings":["Laboratoire de physique de l' \u00c9cole normale sup\u00e9rieure , CNRS , PSL University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire de physique de l' \u00c9cole normale sup\u00e9rieure , CNRS , PSL University ,","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210129651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071388278","display_name":"Ilya M. Nemenman","orcid":"https://orcid.org/0000-0003-3024-4244","observed_orcids":["https://orcid.org/0000-0003-3024-4244"]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Nemenman, Ilya","raw_affiliation_strings":["Department of Physics , Department of Biology, and Initiative for Theory and Modeling of Living Systems , Emory University , Atlanta , Georgia , USA","Sorbonne Universit\u00e9 and"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physics , Department of Biology, and Initiative for Theory and Modeling of Living Systems , Emory University , Atlanta , Georgia , USA","institution_ids":["https://openalex.org/I150468666"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9 and","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064369206","display_name":"Thierry Mora","orcid":"https://orcid.org/0000-0002-5456-9361","observed_orcids":["https://orcid.org/0000-0002-5456-9361"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I4210129651","display_name":"Laboratoire de Physique de l'Ecole Normale Sup\u00e9rieure","ror":"https://ror.org/03a26mh11","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I2746051580","https://openalex.org/I2800004676","https://openalex.org/I29607241","https://openalex.org/I39804081","https://openalex.org/I4210129651"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mora, Thierry","raw_affiliation_strings":["Laboratoire de physique de l' \u00c9cole normale sup\u00e9rieure , CNRS , PSL University ,","Universit\u00e9 de Paris , 75005 Paris , France","Laboratoire de physique de l'ENS - ENS Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire de physique de l' \u00c9cole normale sup\u00e9rieure , CNRS , PSL University ,","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210129651"]},{"raw_affiliation_string":"Universit\u00e9 de Paris , 75005 Paris , France","institution_ids":["https://openalex.org/I204730241"]},{"raw_affiliation_string":"Laboratoire de physique de l'ENS - ENS Paris","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I4210129651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016850339","display_name":"Aleksandra M. Walczak","orcid":"https://orcid.org/0000-0002-2686-5702","observed_orcids":["https://orcid.org/0000-0002-2686-5702"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I4210129651","display_name":"Laboratoire de Physique de l'Ecole Normale Sup\u00e9rieure","ror":"https://ror.org/03a26mh11","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I2746051580","https://openalex.org/I2800004676","https://openalex.org/I29607241","https://openalex.org/I39804081","https://openalex.org/I4210129651"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Walczak, Aleksandra M.","raw_affiliation_strings":["Laboratoire de physique de l' \u00c9cole normale sup\u00e9rieure , CNRS , PSL University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire de physique de l' \u00c9cole normale sup\u00e9rieure , CNRS , PSL University ,","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210129651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13500","display_name":"Probability and Statistical Research","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10968","display_name":"Statistical Distribution Estimation and Applications","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/kullback-leibler-divergence","display_name":"Kullback-Leibler divergence","score":0.9570000171661377},{"id":"https://openalex.org/keywords/divergence-estimation","display_name":"divergence estimation","score":0.8529999852180481},{"id":"https://openalex.org/keywords/bayesian-estimation","display_name":"Bayesian estimation","score":0.7419999837875366},{"id":"https://openalex.org/keywords/categorical-distributions","display_name":"categorical distributions","score":0.7929999828338623},{"id":"https://openalex.org/keywords/markov-chains","display_name":"Markov chains","score":0.8859999775886536},{"id":"https://openalex.org/keywords/random-strings","display_name":"random strings","score":0.5600000023841858},{"id":"https://openalex.org/keywords/small-sample-size","display_name":"small sample size","score":0.5230000019073486}],"concepts":[{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.7548816204071045},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7269585728645325},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6599314212799072},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5998239517211914},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5738312005996704},{"id":"https://openalex.org/C153024298","wikidata":"https://www.wikidata.org/wiki/Q3030678","display_name":"Hellinger distance","level":2,"score":0.5712504386901855},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5706164240837097},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.534668505191803},{"id":"https://openalex.org/C2781280628","wikidata":"https://www.wikidata.org/wiki/Q5280766","display_name":"Dirichlet process","level":3,"score":0.5176461338996887},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4735141098499298},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4423781931400299},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4125789403915405},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2307.04201","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.04201","pdf_url":"https://arxiv.org/pdf/2307.04201","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2307.04201","doi":"https://doi.org/10.48550/arxiv.2307.04201","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2307.04201","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2307.04201","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.04201","pdf_url":"https://arxiv.org/pdf/2307.04201","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3010527862","display_name":null,"funder_award_id":"ANR\u201019","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5617066203","display_name":"NSF-ANR: Precision of collective, distributed, dynamic gene regulation","funder_award_id":"2209996","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7186139688","display_name":"Computational analysis of the response of immune repertoires to viruses","funder_award_id":"ANR-19-CE45-0018","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8747059786","display_name":"Statistical physics of immune-viral co-evolution","funder_award_id":"724208","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384075754.pdf","grobid_xml":"https://content.openalex.org/works/W4384075754.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391776255","https://openalex.org/W2001150023","https://openalex.org/W2955039617","https://openalex.org/W4414879609","https://openalex.org/W137960828","https://openalex.org/W2561586961","https://openalex.org/W7099055048","https://openalex.org/W2270284502","https://openalex.org/W1993778231","https://openalex.org/W2295616284"],"abstract_inverted_index":{"In":[0],"many":[1],"applications":[2],"in":[3],"biology,":[4],"engineering":[5],"and":[6,10,41,94,129],"economics,":[7],"identifying":[8],"similarities":[9],"differences":[11],"between":[12,32,61],"distributions":[13,64,76],"of":[14,24,57,68,71,83,97,127,133],"data":[15,122],"from":[16,91,100],"complex":[17],"processes":[18],"requires":[19],"comparing":[20],"finite":[21],"categorical":[22],"samples":[23,49],"discrete":[25],"counts.":[26],"Statistical":[27],"divergences":[28],"quantify":[29],"the":[30,48,58,75,81,84,105,108],"difference":[31],"two":[33,62,87],"distributions.":[34],"However,":[35],"their":[36],"estimation":[37,116],"is":[38],"very":[39],"difficult":[40],"empirical":[42],"methods":[43],"often":[44],"fail,":[45],"especially":[46],"when":[47],"are":[50],"small.":[51],"We":[52,79,103],"develop":[53],"a":[54,69,124],"Bayesian":[55],"estimator":[56,85],"Kullback-Leibler":[59],"divergence":[60],"probability":[63],"that":[65],"makes":[66],"use":[67],"mixture":[70],"Dirichlet":[72,92],"priors":[73],"on":[74,86],"being":[77],"compared.":[78],"study":[80],"properties":[82],"examples:":[88],"probabilities":[89],"drawn":[90,99],"distributions,":[93],"random":[95],"strings":[96],"letters":[98],"Markov":[101],"chains.":[102],"extend":[104],"approach":[106],"to":[107],"squared":[109],"Hellinger":[110],"divergence.":[111],"Both":[112],"estimators":[113],"outperform":[114],"other":[115],"techniques,":[117],"with":[118,123],"better":[119],"results":[120],"for":[121,130],"large":[125],"number":[126],"categories":[128],"higher":[131],"values":[132],"divergences.":[134]},"counts_by_year":[],"updated_date":"2026-10-22T18:32:59.640997","created_date":"2023-07-13T00:00:00"}