{"id":"https://openalex.org/W2531902758","doi":"https://doi.org/10.1109/allerton.2016.7852287","title":"Phase transitions and optimal algorithms in high-dimensional Gaussian mixture clustering","display_name":"Phase transitions and optimal algorithms in high-dimensional Gaussian mixture clustering","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2531902758","doi":"https://doi.org/10.1109/allerton.2016.7852287","mag":"2531902758"},"language":"en","primary_location":{"id":"doi:10.1109/allerton.2016.7852287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2016.7852287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1610.02918","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Thibault Lesieur","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128565","display_name":"CEA Paris-Saclay","ror":"https://ror.org/03n15ch10","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210128565"]},{"id":"https://openalex.org/I4210163633","display_name":"Institut de Physique Th\u00e9orique","ror":"https://ror.org/058rvd314","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I2738703131","https://openalex.org/I2738703131","https://openalex.org/I4210098836","https://openalex.org/I4210113668","https://openalex.org/I4210163633"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"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/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Thibault Lesieur","raw_affiliation_strings":["Institut de Physique Th\u00e9orique, CNRS, CEA, Universit\u00e9 Paris-Saclay, Gif-sur-Yvette, France"],"affiliations":[{"raw_affiliation_string":"Institut de Physique Th\u00e9orique, CNRS, CEA, Universit\u00e9 Paris-Saclay, Gif-sur-Yvette, France","institution_ids":["https://openalex.org/I4210163633","https://openalex.org/I277688954","https://openalex.org/I1294671590","https://openalex.org/I4210128565","https://openalex.org/I2738703131"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Caterina de Bacco","orcid":null},"institutions":[{"id":"https://openalex.org/I1308548392","display_name":"Santa Fe Institute","ror":"https://ror.org/01arysc35","country_code":"US","type":"funder","lineage":["https://openalex.org/I1308548392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caterina de Bacco","raw_affiliation_strings":["Santa Fe Institute, New Mexico, USA"],"affiliations":[{"raw_affiliation_string":"Santa Fe Institute, New Mexico, USA","institution_ids":["https://openalex.org/I1308548392"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jess Banks","orcid":null},"institutions":[{"id":"https://openalex.org/I1308548392","display_name":"Santa Fe Institute","ror":"https://ror.org/01arysc35","country_code":"US","type":"funder","lineage":["https://openalex.org/I1308548392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jess Banks","raw_affiliation_strings":["Santa Fe Institute, New Mexico, USA"],"affiliations":[{"raw_affiliation_string":"Santa Fe Institute, New Mexico, USA","institution_ids":["https://openalex.org/I1308548392"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Florent Krzakala","orcid":null},"institutions":[{"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/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/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Florent Krzakala","raw_affiliation_strings":["Laboratoire de Physique Statistique, CNRS, PSL Universit\u00e9s & Ecole Normale Sup\u00e9rieure, Sorbonne Universit\u00e9s et Universit\u00e9 Pierre & Marie Curie, Paris, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire de Physique Statistique, CNRS, PSL Universit\u00e9s & Ecole Normale Sup\u00e9rieure, Sorbonne Universit\u00e9s et Universit\u00e9 Pierre & Marie Curie, Paris, France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I2746051580","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cris Moore","orcid":null},"institutions":[{"id":"https://openalex.org/I1308548392","display_name":"Santa Fe Institute","ror":"https://ror.org/01arysc35","country_code":"US","type":"funder","lineage":["https://openalex.org/I1308548392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cris Moore","raw_affiliation_strings":["Santa Fe Institute, New Mexico, USA"],"affiliations":[{"raw_affiliation_string":"Santa Fe Institute, New Mexico, USA","institution_ids":["https://openalex.org/I1308548392"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lenka Zdeborova","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163633","display_name":"Institut de Physique Th\u00e9orique","ror":"https://ror.org/058rvd314","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I2738703131","https://openalex.org/I2738703131","https://openalex.org/I4210098836","https://openalex.org/I4210113668","https://openalex.org/I4210163633"]},{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210128565","display_name":"CEA Paris-Saclay","ror":"https://ror.org/03n15ch10","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210128565"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lenka Zdeborova","raw_affiliation_strings":["Institut de Physique Th\u00e9orique, CNRS, CEA, Universit\u00e9 Paris-Saclay, Gif-sur-Yvette, France"],"affiliations":[{"raw_affiliation_string":"Institut de Physique Th\u00e9orique, CNRS, CEA, Universit\u00e9 Paris-Saclay, Gif-sur-Yvette, France","institution_ids":["https://openalex.org/I4210163633","https://openalex.org/I277688954","https://openalex.org/I1294671590","https://openalex.org/I4210128565","https://openalex.org/I2738703131"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210128565","https://openalex.org/I4210163633"],"apc_list":null,"apc_paid":null,"fwci":2.2162,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89130931,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"601","last_page":"608"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11716","display_name":"Random Matrices and Applications","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11716","display_name":"Random Matrices and Applications","score":0.9993000030517578,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9993000030517578,"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/T11152","display_name":"Stochastic processes and statistical mechanics","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/2610","display_name":"Mathematical Physics"},"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/cluster-analysis","display_name":"Cluster analysis","score":0.7371000051498413},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5613999962806702},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.5601000189781189},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5504999756813049},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.42170000076293945},{"id":"https://openalex.org/keywords/phase-transition","display_name":"Phase transition","score":0.3831999897956848},{"id":"https://openalex.org/keywords/determining-the-number-of-clusters-in-a-data-set","display_name":"Determining the number of clusters in a data set","score":0.3765999972820282},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.36489999294281006},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.33399999141693115}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7371000051498413},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6129999756813049},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5716999769210815},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5613999962806702},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5601000189781189},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5504999756813049},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C149288129","wikidata":"https://www.wikidata.org/wiki/Q185357","display_name":"Phase transition","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C149872217","wikidata":"https://www.wikidata.org/wiki/Q5265701","display_name":"Determining the number of clusters in a data set","level":5,"score":0.3765999972820282},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.3499999940395355},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.33399999141693115},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.3125},{"id":"https://openalex.org/C196298200","wikidata":"https://www.wikidata.org/wiki/Q577705","display_name":"Critical point (mathematics)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C64413873","wikidata":"https://www.wikidata.org/wiki/Q21005","display_name":"Threshold limit value","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.29750001430511475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.29589998722076416},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2775000035762787},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.2736999988555908},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.272599995136261},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C207968372","wikidata":"https://www.wikidata.org/wiki/Q310401","display_name":"k-means clustering","level":3,"score":0.26019999384880066}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/allerton.2016.7852287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2016.7852287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1610.02918","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1610.02918","pdf_url":"https://arxiv.org/pdf/1610.02918","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1610.02918","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1610.02918","pdf_url":"https://arxiv.org/pdf/1610.02918","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1922029667","https://openalex.org/W1976408035","https://openalex.org/W1990755770","https://openalex.org/W1992669500","https://openalex.org/W2034451938","https://openalex.org/W2034857737","https://openalex.org/W2040969041","https://openalex.org/W2053881994","https://openalex.org/W2066459155","https://openalex.org/W2067038358","https://openalex.org/W2086177078","https://openalex.org/W2150593711","https://openalex.org/W2151781750","https://openalex.org/W2332917886","https://openalex.org/W2508909698","https://openalex.org/W2566505556","https://openalex.org/W2610971674","https://openalex.org/W2963072996","https://openalex.org/W2964282092","https://openalex.org/W6674881146","https://openalex.org/W6718058154"],"related_works":[],"abstract_inverted_index":{"We":[0,67],"consider":[1],"the":[2,9,13,41,47,50,60,70,74,84,99,106],"problem":[3],"of":[4,16,44,86],"Gaussian":[5],"mixture":[6],"clustering":[7],"in":[8,19],"high-dimensional":[10],"limit":[11],"where":[12],"data":[14],"consists":[15],"m":[17],"points":[18],"n":[20],"dimensions,":[21],"n,m":[22],"\u2192":[23],"\u221e":[24],"and":[25,46,105],"\u03b1":[26,45],"=":[27],"m/n":[28],"stays":[29],"finite.":[30],"Using":[31],"exact":[32],"but":[33],"non-rigorous":[34],"methods":[35],"from":[36],"statistical":[37],"physics,":[38],"we":[39,80],"determine":[40,69],"critical":[42],"value":[43],"distance":[48],"between":[49,98],"clusters":[51,63,87],"at":[52,108],"which":[53,109],"it":[54],"becomes":[55],"information-theoretically":[56,102],"possible":[57],"to":[58],"reconstruct":[59],"membership":[61],"into":[62],"better":[64],"than":[65],"chance.":[66],"also":[68],"accuracy":[71],"achievable":[72],"by":[73],"Bayes-optimal":[75],"estimation":[76],"algorithm.":[77],"In":[78],"particular,":[79],"find":[81],"that":[82],"when":[83],"number":[85],"is":[88,95],"sufficiently":[89],"large,":[90],"r":[91],">":[92],"4+2\u221a\u03b1,":[93],"there":[94],"a":[96],"gap":[97],"threshold":[100,107],"for":[101],"optimal":[103],"performance":[104],"known":[110],"algorithms":[111],"succeed.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2016-10-21T00:00:00"}