{"id":"https://openalex.org/W2432836740","doi":"https://doi.org/10.48550/arxiv.1606.05100","title":"PECOK: a convex optimization approach to variable clustering","display_name":"PECOK: a convex optimization approach to variable clustering","publication_year":2016,"publication_date":"2016-06-16","ids":{"openalex":"https://openalex.org/W2432836740","doi":"https://doi.org/10.48550/arxiv.1606.05100","mag":"2432836740"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1606.05100","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1606.05100","pdf_url":"https://arxiv.org/pdf/1606.05100","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/1606.05100","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021259214","display_name":"Florentina Bunea","orcid":"https://orcid.org/0000-0002-1291-1210","observed_orcids":["https://orcid.org/0000-0002-1291-1210"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bunea, Florentina","raw_affiliation_strings":["Cornell University [New York]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University [New York]","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Giraud, Christophe","orcid":null,"observed_orcids":[]},"institutions":[{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Giraud, Christophe","raw_affiliation_strings":["Universit\u00e9 Paris-Saclay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay","institution_ids":["https://openalex.org/I277688954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018696127","display_name":"Martin Royer","orcid":"https://orcid.org/0000-0002-5911-1907","observed_orcids":["https://orcid.org/0000-0002-5911-1907"]},"institutions":[{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Royer, Martin","raw_affiliation_strings":["Universit\u00e9 Paris-Saclay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay","institution_ids":["https://openalex.org/I277688954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054772316","display_name":"Nicolas Verz\u00e9len","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210117045","display_name":"Math\u00e9matiques, Informatique et Statistique pour l'Environnement et l'Agronomie","ror":"https://ror.org/01pd2sz18","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210088668","https://openalex.org/I4210117045","https://openalex.org/I4210117091","https://openalex.org/I4399657933"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Verzelen, Nicolas","raw_affiliation_strings":["Math\u00e9matiques, Informatique et STatistique pour l'Environnement et l'Agronomie"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Math\u00e9matiques, Informatique et STatistique pour l'Environnement et l'Agronomie","institution_ids":["https://openalex.org/I4210117045"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"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/T10136","display_name":"Statistical Methods and Inference","score":0.635699987411499,"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/T10136","display_name":"Statistical Methods and Inference","score":0.635699987411499,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.26589998602867126,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.08129999786615372,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/variable-clustering","display_name":"variable clustering","score":0.9940000176429749},{"id":"https://openalex.org/keywords/convex-relaxation","display_name":"convex relaxation","score":0.6600000262260437},{"id":"https://openalex.org/keywords/k-means-clustering","display_name":"K-means clustering","score":0.8119999766349792},{"id":"https://openalex.org/keywords/semidefinite-programming","display_name":"semidefinite programming","score":0.8040000200271606},{"id":"https://openalex.org/keywords/cluster-separation","display_name":"cluster separation","score":0.4790000021457672},{"id":"https://openalex.org/keywords/minimax-lower-bounds","display_name":"minimax lower bounds","score":0.8970000147819519},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"spectral clustering","score":0.7329999804496765},{"id":"https://openalex.org/keywords/high-dimensional-data-clustering","display_name":"high-dimensional data clustering","score":0.7120000123977661},{"id":"https://openalex.org/keywords/adaptive-number-of-clusters","display_name":"adaptive number of clusters","score":0.6940000057220459}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6242197155952454},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5759952068328857},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.48080864548683167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44045209884643555},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.397713840007782},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33585166931152344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24474939703941345},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.05216383934020996},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1606.05100","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1606.05100","pdf_url":"https://arxiv.org/pdf/1606.05100","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":"pmh:oai:HAL:hal-02966884v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.inrae.fr/hal-02966884","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2020","raw_type":"info:eu-repo/semantics/preprint"},{"id":"doi:10.48550/arxiv.1606.05100","doi":"https://doi.org/10.48550/arxiv.1606.05100","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1606.05100","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1606.05100","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1606.05100","pdf_url":"https://arxiv.org/pdf/1606.05100","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1546146584","https://openalex.org/W1560153690","https://openalex.org/W1577111082","https://openalex.org/W1803708361","https://openalex.org/W1847799989","https://openalex.org/W1855425795","https://openalex.org/W1986219860","https://openalex.org/W2073459066","https://openalex.org/W2110105238","https://openalex.org/W2110340112","https://openalex.org/W2141012957","https://openalex.org/W2150593711","https://openalex.org/W2210515221","https://openalex.org/W2302206641","https://openalex.org/W2524946712","https://openalex.org/W3100144903"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2600246793","https://openalex.org/W4238204885"],"abstract_inverted_index":{"The":[0,117],"problem":[1],"of":[2,7,11,24,37,52,94,145,159,175],"variable":[3],"clustering":[4,62],"is":[5,29,64,147],"that":[6,85,137,165],"grouping":[8],"similar":[9],"components":[10],"a":[12,40,49,79,90,99,128,135],"$p$-dimensional":[13],"vector":[14],"$X=(X_{1},\\ldots,X_{p})$,":[15],"and":[16,44,77,107,163],"estimating":[17],"these":[18],"groups":[19,36,45],"from":[20,150],"$n$":[21],"independent":[22],"copies":[23],"$X$.":[25],"When":[26],"cluster":[27,75,100,115,132,173],"similarity":[28],"defined":[30],"via":[31],"$G$-latent":[32,105],"models,":[33,106],"in":[34],"which":[35],"$X$-variables":[38],"have":[39],"common":[41],"latent":[42],"generator,":[43],"are":[46,122],"relative":[47],"to":[48,73,104,124],"partition":[50],"$G$":[51,126],"the":[53,59,143,151,166,169],"index":[54],"set":[55],"$\\{1,":[56],"\\ldots,":[57],"p\\}$,":[58],"most":[60],"natural":[61],"strategy":[63,70],"$K$-means.":[65],"We":[66,97,153],"explain":[67],"why":[68],"this":[69],"cannot":[71],"lead":[72],"perfect":[74,114,172],"recovery":[76,174],"offer":[78],"correction,":[80],"based":[81],"on":[82],"semi-definite":[83],"programing,":[84],"can":[86],"be":[87],"viewed":[88],"as":[89],"penalized":[91],"convex":[92],"relaxation":[93],"$K$-means":[95],"(PECOK).":[96],"introduce":[98],"separation":[101,133],"measure":[102],"tailored":[103],"derive":[108],"its":[109],"minimax":[110,130],"lower":[111],"bound":[112],"for":[113,171],"recovery.":[116],"clusters":[118],"estimated":[119,148],"by":[120],"PECOK":[121,155],"shown":[123],"recover":[125],"at":[127],"near":[129],"optimal":[131],"rate,":[134],"result":[136],"holds":[138],"true":[139],"even":[140],"if":[141],"$K$,":[142],"number":[144],"clusters,":[146],"adaptively":[149],"data.":[152],"compare":[154],"with":[156],"appropriate":[157],"corrections":[158],"spectral":[160],"clustering-type":[161],"procedures,":[162],"show":[164],"former":[167],"outperforms":[168],"latter":[170],"minimally":[176],"separated":[177],"clusters.":[178]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-10-19T09:35:57.686232","created_date":"2025-10-10T00:00:00"}