{"id":"https://openalex.org/W2276728651","doi":"https://doi.org/10.5555/2789272.2912116","title":"Condition for perfect dimensionality recovery by variational Bayesian PCA","display_name":"Condition for perfect dimensionality recovery by variational Bayesian PCA","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2276728651","doi":"https://doi.org/10.5555/2789272.2912116","mag":"2276728651"},"language":"en","primary_location":{"id":"mag:2276728651","is_oa":false,"landing_page_url":"http://jmlr.org/papers/volume16/nakajima15a/nakajima15a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research","raw_type":null},"type":"article","indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034738514","display_name":"Shinichi Nakajima","orcid":"https://orcid.org/0000-0003-3970-4569"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shinichi Nakajima","raw_affiliation_strings":["Berlin Big Data Center, Technische Universit\u00e4t Berlin, Berlin, Germany#TAB#"],"raw_orcid":"https://orcid.org/0000-0003-3970-4569","affiliations":[{"raw_affiliation_string":"Berlin Big Data Center, Technische Universit\u00e4t Berlin, Berlin, Germany#TAB#","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110293322","display_name":"Ryota Tomioka","orcid":"https://orcid.org/0000-0002-8092-6553"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryota Tomioka","raw_affiliation_strings":["Toyota Technological Institute at Chicago, Chicago IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, Chicago IL","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072744508","display_name":"Masashi Sugiyama","orcid":"https://orcid.org/0000-0001-6658-6743"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Sugiyama","raw_affiliation_strings":["Department of Complexity Science and Engineering; The University of Tokyo; Tokyo Japan"],"raw_orcid":"https://orcid.org/0000-0001-6658-6743","affiliations":[{"raw_affiliation_string":"Department of Complexity Science and Engineering; The University of Tokyo; Tokyo Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107868098","display_name":"S. Derin Babacan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Derin Babacan","raw_affiliation_strings":["Google, Inc, Mountain View, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc, Mountain View, CA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9288,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.94380494,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"16","issue":"1","first_page":"3757","last_page":"3811"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9994999766349792,"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":0.9994999766349792,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.8346161842346191},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5558906197547913},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4989297389984131},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4921573996543884},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.47220712900161743},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4595905542373657},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.4504580497741699},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4441562294960022},{"id":"https://openalex.org/keywords/sparse-pca","display_name":"Sparse PCA","score":0.4324984848499298},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4318525791168213},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.42837023735046387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4241960346698761},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4232054352760315},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36619478464126587},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35373902320861816},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33956217765808105},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1298178732395172},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08184972405433655}],"concepts":[{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.8346161842346191},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5558906197547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4989297389984131},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4921573996543884},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.47220712900161743},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4595905542373657},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.4504580497741699},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4441562294960022},{"id":"https://openalex.org/C24252448","wikidata":"https://www.wikidata.org/wiki/Q7573786","display_name":"Sparse PCA","level":3,"score":0.4324984848499298},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4318525791168213},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.42837023735046387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4241960346698761},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4232054352760315},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36619478464126587},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35373902320861816},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33956217765808105},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1298178732395172},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08184972405433655},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2276728651","is_oa":false,"landing_page_url":"http://jmlr.org/papers/volume16/nakajima15a/nakajima15a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Journal of Machine Learning Research","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W16456489","https://openalex.org/W63320859","https://openalex.org/W69540849","https://openalex.org/W1496451467","https://openalex.org/W1506806321","https://openalex.org/W1506954757","https://openalex.org/W1507695701","https://openalex.org/W1520752838","https://openalex.org/W1586554030","https://openalex.org/W1618600317","https://openalex.org/W1663973292","https://openalex.org/W1880262756","https://openalex.org/W1920010643","https://openalex.org/W1988837127","https://openalex.org/W2005522417","https://openalex.org/W2005695907","https://openalex.org/W2030769153","https://openalex.org/W2034857737","https://openalex.org/W2060581589","https://openalex.org/W2072184935","https://openalex.org/W2091571775","https://openalex.org/W2095687430","https://openalex.org/W2103139809","https://openalex.org/W2106084579","https://openalex.org/W2107418674","https://openalex.org/W2107710506","https://openalex.org/W2113474244","https://openalex.org/W2115120746","https://openalex.org/W2116123504","https://openalex.org/W2118550318","https://openalex.org/W2125027820","https://openalex.org/W2129638195","https://openalex.org/W2133028937","https://openalex.org/W2137245235","https://openalex.org/W2161497029","https://openalex.org/W2167448284","https://openalex.org/W2294460823","https://openalex.org/W2328187444","https://openalex.org/W2535123820"],"related_works":["https://openalex.org/W2115120746","https://openalex.org/W2125027820","https://openalex.org/W63320859","https://openalex.org/W2133028937","https://openalex.org/W1920010643","https://openalex.org/W1663973292","https://openalex.org/W2467553673","https://openalex.org/W69540849","https://openalex.org/W2095687430","https://openalex.org/W2071128523","https://openalex.org/W2147036700","https://openalex.org/W2941256613","https://openalex.org/W3034515071","https://openalex.org/W2282795067","https://openalex.org/W3098803551","https://openalex.org/W2106754084","https://openalex.org/W3003552232","https://openalex.org/W1982487445","https://openalex.org/W2946453360","https://openalex.org/W2225803984"],"abstract_inverted_index":{"Having":[0],"shown":[1],"its":[2,26],"good":[3],"performance":[4,27,81],"in":[5,43,65,121],"many":[6],"applications,":[7],"variational":[8],"Bayesian":[9,23],"(VB)":[10],"learning":[11,42,120],"is":[12],"known":[13],"to":[14,22,74],"be":[15],"one":[16],"of":[17,40,82,94,106,129,151],"the":[18,38,66,70,80,85,91,104,130,142],"best":[19],"tractable":[20],"approximations":[21],"learning.":[24],"However,":[25],"was":[28],"not":[29],"well":[30],"understood":[31],"theoretically.":[32],"In":[33,123],"this":[34],"paper,":[35],"we":[36,52,117,126],"clarify":[37],"behavior":[39],"VB":[41,95,119],"probabilistic":[44],"PCA":[45],"(or":[46,62],"fully-observed":[47],"matrix":[48,71],"factorization).":[49],"More":[50],"specifically,":[51],"establish":[53],"a":[54,98,135],"necessary":[55],"and":[56,134,137],"sufficient":[57],"condition":[58],"for":[59,141,149],"perfect":[60],"dimensionality":[61,114],"rank)":[63],"recovery":[64],"large-scale":[67],"limit":[68],"when":[69],"size":[72],"goes":[73],"infinity.":[75],"Our":[76],"result":[77],"theoretically":[78],"guarantees":[79],"VB-PCA.":[83,152],"At":[84],"same":[86],"time,":[87],"it":[88],"also":[89],"reveals":[90],"conservative":[92],"nature":[93],"learning--it":[96],"offers":[97],"low":[99,107],"false":[100],"positive":[101],"rate":[102],"at":[103],"expense":[105],"sensitivity.":[108],"By":[109],"contrasting":[110],"with":[111],"an":[112],"alternative":[113],"selection":[115],"method,":[116],"characterize":[118],"PCA.":[122],"our":[124],"analysis,":[125],"obtain":[127],"bounds":[128],"noise":[131],"variance":[132],"estimator,":[133],"new":[136],"simple":[138],"analytic-form":[139],"solution":[140],"other":[143],"parameters,":[144],"which":[145],"themselves":[146],"are":[147],"useful":[148],"implementation":[150]},"counts_by_year":[{"year":2019,"cited_by_count":28},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-10-10T17:16:08.811792","created_date":"2025-10-10T00:00:00"}