{"id":"https://openalex.org/W2171813245","doi":"https://doi.org/10.5555/1577069.1577092","title":"Nearest Neighbor Clustering: A Baseline Method for Consistent Clustering with Arbitrary Objective Functions","display_name":"Nearest Neighbor Clustering: A Baseline Method for Consistent Clustering with Arbitrary Objective Functions","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2171813245","doi":"https://doi.org/10.5555/1577069.1577092","mag":"2171813245"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.165.8641","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.165.8641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.kyb.tuebingen.mpg.de/publications/attachments/BubeckLuxburg09_5687%5B1%5D.pdf","raw_type":"text"},"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00185780","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021842384","display_name":"S\u00e9bastien Bubeck","orcid":"https://orcid.org/0000-0001-9122-4410"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S\u00e9bastien Bubeck","raw_affiliation_strings":["Sequential Learning"],"raw_orcid":"https://orcid.org/0000-0001-9122-4410","affiliations":[{"raw_affiliation_string":"Sequential Learning","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083754306","display_name":"Ulrike von Luxburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112925","display_name":"Max Planck Institute for Biological Cybernetics","ror":"https://ror.org/026nmvv73","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210112925"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ulrike von Luxburg","raw_affiliation_strings":["Max Planck Institute for Biological Cybernetics,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Biological Cybernetics,","institution_ids":["https://openalex.org/I4210112925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.2179,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.9645456,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"10","issue":"23","first_page":"657","last_page":"698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9994000196456909,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9994000196456909,"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":0.9990000128746033,"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/T11106","display_name":"Data Management and Algorithms","score":0.9884999990463257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8074278831481934},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5940787196159363},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.5746012926101685},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5370383262634277},{"id":"https://openalex.org/keywords/constrained-clustering","display_name":"Constrained clustering","score":0.5295972228050232},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.45206791162490845},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.4479557275772095},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.44351476430892944},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.4286472201347351},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.4143250584602356},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.37909823656082153},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3702576458454132},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35651862621307373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3520044684410095},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33274561166763306}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8074278831481934},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5940787196159363},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.5746012926101685},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5370383262634277},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.5295972228050232},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.45206791162490845},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.4479557275772095},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.44351476430892944},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.4286472201347351},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.4143250584602356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.37909823656082153},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3702576458454132},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35651862621307373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3520044684410095},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33274561166763306}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.165.8641","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.165.8641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.kyb.tuebingen.mpg.de/publications/attachments/BubeckLuxburg09_5687%5B1%5D.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00185780v3","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00185780","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,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2011","raw_type":"info:eu-repo/semantics/preprint"},{"id":"pmh:oai:edoc.mpg.de:461634","is_oa":false,"landing_page_url":"http://edoc.mpg.de/461634","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research, v.10, 657-698 (2009)","raw_type":"Article"},{"id":"pmh:oai:pure.mpg.de:item_1789450","is_oa":false,"landing_page_url":"https://hdl.handle.net/11858/00-001M-0000-0013-C591-8","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The Journal of Machine Learning Research","raw_type":"info:eu-repo/semantics/article"},{"id":"mag:2171813245","is_oa":false,"landing_page_url":"https://www.microsoft.com/en-us/research/wp-content/uploads/2017/01/bubeck09a.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":{"id":"pmh:oai:HAL:inria-00185780v3","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00185780","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,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2011","raw_type":"info:eu-repo/semantics/preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W115754844","https://openalex.org/W809692800","https://openalex.org/W1483985387","https://openalex.org/W1558476308","https://openalex.org/W1564947197","https://openalex.org/W1578468649","https://openalex.org/W1579271636","https://openalex.org/W1940950356","https://openalex.org/W2001907516","https://openalex.org/W2002276939","https://openalex.org/W2004343933","https://openalex.org/W2010353172","https://openalex.org/W2015245929","https://openalex.org/W2015953751","https://openalex.org/W2033652300","https://openalex.org/W2034331023","https://openalex.org/W2045756072","https://openalex.org/W2047555270","https://openalex.org/W2048675583","https://openalex.org/W2050516752","https://openalex.org/W2067462817","https://openalex.org/W2067976091","https://openalex.org/W2085080020","https://openalex.org/W2086943813","https://openalex.org/W2088912280","https://openalex.org/W2101460669","https://openalex.org/W2132914434","https://openalex.org/W2156909104","https://openalex.org/W2162818082","https://openalex.org/W2166076290","https://openalex.org/W2989661724"],"related_works":["https://openalex.org/W66189505","https://openalex.org/W2067462817","https://openalex.org/W2918668824","https://openalex.org/W1855075141","https://openalex.org/W3016361179","https://openalex.org/W2963090360","https://openalex.org/W2606287509","https://openalex.org/W1495861513","https://openalex.org/W2204093302","https://openalex.org/W2964294052","https://openalex.org/W2782833507","https://openalex.org/W2954508149","https://openalex.org/W2775465138","https://openalex.org/W2141729166","https://openalex.org/W2132914434","https://openalex.org/W2121947440","https://openalex.org/W2016381774","https://openalex.org/W1794340831","https://openalex.org/W1656501588","https://openalex.org/W2889658189"],"abstract_inverted_index":{"Clustering":[0],"is":[1,11,48,101],"often":[2],"formulated":[3],"as":[4,154],"a":[5,132,155],"discrete":[6],"optimization":[7,72,124],"problem.":[8],"The":[9],"objective":[10,162,175],"to\\nfind,":[12],"among":[13],"all":[14,171],"partitions":[15],"of":[16,55,64,106],"the":[17,20,29,36,46,52,56,61,65,95,99,104,107],"data":[18,38],"set,":[19],"best":[21,53],"one":[22,127],"according":[23],"to":[24,50,59,102,142,158],"some":[25,43],"quality":[26],"measure.\\nHowever,":[27],"in":[28,94,146],"statistical":[30],"setting":[31],"where":[32],"we":[33,116,136],"assume":[34],"that":[35,70,166],"finite":[37],"set":[39],"has":[40],"been":[41],"sampled\\nfrom":[42],"underlying":[44,66],"space,":[45],"goal":[47],"not":[49,76],"find":[51],"partition":[54,63],"given\\nsample,":[57],"but":[58],"approximate":[60],"true":[62],"space.":[67],"We":[68,85,164],"argue":[69],"the\\ndiscrete":[71],"approach":[73],"usually":[74],"does":[75],"achieve":[77],"this":[78,91,149],"goal,":[79],"and":[80],"instead":[81],"can":[82,117,151],"lead":[83],"to\\ninconsistency.":[84],"construct":[86],"examples":[87],"which":[88],"provably":[89],"have":[90],"behavior.":[92],"As":[93,126],"case\\nof":[96],"supervised":[97,147],"learning,":[98,148],"cure":[100],"restrict":[103],"size":[105],"function":[108,114,134],"classes":[109,115],"under":[110],"consideration.\\nFor":[111],"appropriate":[112],"\u0093small\u0094":[113],"prove":[118,165],"very":[119],"general":[120],"consistency\\ntheorems":[121],"for":[122,130,170],"clustering":[123,161,174],"schemes.":[125],"particular":[128],"algorithm":[129,150,157],"clustering\\nwith":[131],"restricted":[133],"space":[135],"introduce":[137],"\u0093nearest":[138],"neighbor":[139,144],"clustering\u0094.":[140],"Similar":[141],"the\\nk-nearest":[143],"classifier":[145],"be":[152],"seen":[153],"general\\nbaseline":[156],"minimize":[159],"arbitrary":[160],"functions.":[163,176],"it\\nis":[167],"statistically":[168],"consistent":[169],"commonly":[172],"used":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":5}],"updated_date":"2025-10-10T17:16:08.811792","created_date":"2025-10-10T00:00:00"}