{"id":"https://openalex.org/W2068193083","doi":"https://doi.org/10.1109/gensips.2013.6735934","title":"On the optimality of k-means clustering","display_name":"On the optimality of k-means clustering","publication_year":2013,"publication_date":"2013-11-01","ids":{"openalex":"https://openalex.org/W2068193083","doi":"https://doi.org/10.1109/gensips.2013.6735934","mag":"2068193083"},"language":"en","primary_location":{"id":"doi:10.1109/gensips.2013.6735934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gensips.2013.6735934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Workshop on Genomic Signal Processing and Statistics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5037999551","display_name":"Lori A. Dalton","orcid":"https://orcid.org/0000-0001-8715-5723"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lori A. Dalton","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering and Dept. of Biomedical Informatics The Ohio State University, Columbus, OH, USA","Dept. of Electr. & Comput. Eng., Ohio state Univ., Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering and Dept. of Biomedical Informatics The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Ohio state Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5037999551"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.7045,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67218591,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"70","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9973000288009644,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9973000288009644,"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/T10770","display_name":"Soil Geostatistics and Mapping","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental 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":0.9864000082015991,"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/cluster-analysis","display_name":"Cluster analysis","score":0.875684380531311},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.5916253328323364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5823959112167358},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.519869327545166},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4355200529098511},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4101126790046692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38483762741088867},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3586193323135376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33179980516433716},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32792824506759644},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.320919394493103}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.875684380531311},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.5916253328323364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5823959112167358},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.519869327545166},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4355200529098511},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4101126790046692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38483762741088867},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3586193323135376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33179980516433716},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32792824506759644},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.320919394493103}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gensips.2013.6735934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gensips.2013.6735934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Workshop on Genomic Signal Processing and Statistics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1992419399","https://openalex.org/W2137784044","https://openalex.org/W2154231035","https://openalex.org/W4244494905"],"related_works":["https://openalex.org/W1999117613","https://openalex.org/W2040929534","https://openalex.org/W3022637481","https://openalex.org/W2393816671","https://openalex.org/W3120229345","https://openalex.org/W2111119584","https://openalex.org/W3144143113","https://openalex.org/W3039964395","https://openalex.org/W2804957450","https://openalex.org/W2357208913"],"abstract_inverted_index":{"Although":[0],"it":[1,16],"is":[2,8,17,74,101],"typically":[3],"accepted":[4],"that":[5],"cluster":[6],"analysis":[7],"a":[9,41,56,78],"subjective":[10,79],"activity,":[11],"without":[12],"an":[13,82],"objective":[14,83],"framework":[15],"impossible":[18],"to":[19,39,81,112],"understand,":[20],"let":[21],"alone":[22],"guarantee,":[23],"the":[24,93,104],"predictive":[25],"capacity":[26],"of":[27,44],"clustering.":[28,45],"To":[29],"address":[30],"this,":[31],"recent":[32],"work":[33],"utilizes":[34],"random":[35],"point":[36],"process":[37],"theory":[38,43,47,52],"develop":[40],"probabilistic":[42],"The":[46],"fully":[48],"parallels":[49],"Bayes":[50,66,106],"decision":[51],"for":[53],"classification:":[54],"given":[55],"known":[57],"underlying":[58],"processes":[59],"and":[60,109],"specified":[61],"cost":[62],"function":[63,95],"there":[64],"exist":[65],"clustering":[67,100,107],"operators":[68],"with":[69],"minimum":[70],"expected":[71],"error.":[72],"Clustering":[73],"hence":[75],"transformed":[76],"from":[77],"activity":[80],"operation.":[84],"In":[85],"this":[86,114],"work,":[87],"we":[88],"present":[89],"conditions":[90],"under":[91],"which":[92],"optimization":[94],"utilized":[96],"in":[97,103],"classical":[98],"k-means":[99],"optimal":[102],"new":[105],"theory,":[108],"thus":[110],"begin":[111],"understand":[113],"algorithm":[115],"objectively.":[116]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}