{"id":"https://openalex.org/W4403395446","doi":"https://doi.org/10.1080/10618600.2024.2414889","title":"Scalable Clustering: Large Scale Unsupervised Learning of Gaussian Mixture Models with Outliers","display_name":"Scalable Clustering: Large Scale Unsupervised Learning of Gaussian Mixture Models with Outliers","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4403395446","doi":"https://doi.org/10.1080/10618600.2024.2414889"},"language":"en","primary_location":{"id":"doi:10.1080/10618600.2024.2414889","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2024.2414889","pdf_url":null,"source":{"id":"https://openalex.org/S76159266","display_name":"Journal of Computational and Graphical Statistics","issn_l":"1061-8600","issn":["1061-8600","1537-2715"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational and Graphical Statistics","raw_type":"journal-article"},"type":"article","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/A5054616235","display_name":"Yijia Zhou","orcid":"https://orcid.org/0000-0002-5633-7564"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yijia Zhou","raw_affiliation_strings":["Department of Mathematics, Florida State University","Department of Mathematics, Florida State University, Tallahassee, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Florida State University","institution_ids":["https://openalex.org/I103163165"]},{"raw_affiliation_string":"Department of Mathematics, Florida State University, Tallahassee, FL","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018426276","display_name":"Kyle A. Gallivan","orcid":"https://orcid.org/0000-0003-4572-4240"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle A. Gallivan","raw_affiliation_strings":["Department of Mathematics, Florida State University","Department of Mathematics, Florida State University, Tallahassee, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Florida State University","institution_ids":["https://openalex.org/I103163165"]},{"raw_affiliation_string":"Department of Mathematics, Florida State University, Tallahassee, FL","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052175239","display_name":"Adrian Barbu","orcid":"https://orcid.org/0000-0002-9548-7872"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adrian Barbu","raw_affiliation_strings":["Department of Statistics, Florida State University","Department of Statistics, Florida State University, Tallahassee, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Florida State University","institution_ids":["https://openalex.org/I103163165"]},{"raw_affiliation_string":"Department of Statistics, Florida State University, Tallahassee, FL","institution_ids":["https://openalex.org/I103163165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5054616235"],"corresponding_institution_ids":["https://openalex.org/I103163165"],"apc_list":null,"apc_paid":null,"fwci":0.8335,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77924376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"34","issue":"3","first_page":"884","last_page":"895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9998999834060669,"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":0.9998999834060669,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9962000250816345,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9747999906539917,"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":0.6837905645370483},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6446756720542908},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6066613793373108},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5980992317199707},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5734962224960327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5417495369911194},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5209242701530457},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.44741290807724},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44142279028892517},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38055458664894104},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32496970891952515},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07605376839637756}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6837905645370483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6446756720542908},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6066613793373108},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5980992317199707},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5734962224960327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5417495369911194},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5209242701530457},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.44741290807724},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44142279028892517},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38055458664894104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32496970891952515},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07605376839637756},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/10618600.2024.2414889","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2024.2414889","pdf_url":null,"source":{"id":"https://openalex.org/S76159266","display_name":"Journal of Computational and Graphical Statistics","issn_l":"1061-8600","issn":["1061-8600","1537-2715"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational and Graphical Statistics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W200434350","https://openalex.org/W1480242538","https://openalex.org/W1973264045","https://openalex.org/W1978627835","https://openalex.org/W1980018091","https://openalex.org/W1998871699","https://openalex.org/W2007339694","https://openalex.org/W2014565165","https://openalex.org/W2022852240","https://openalex.org/W2033852356","https://openalex.org/W2041565863","https://openalex.org/W2049633694","https://openalex.org/W2084134149","https://openalex.org/W2117539524","https://openalex.org/W2121947440","https://openalex.org/W2132914434","https://openalex.org/W2134199473","https://openalex.org/W2139339877","https://openalex.org/W2146758737","https://openalex.org/W2150593711","https://openalex.org/W2165874743","https://openalex.org/W2187089797","https://openalex.org/W2415715393","https://openalex.org/W2890346520","https://openalex.org/W2938284053","https://openalex.org/W2940320374","https://openalex.org/W2946720770","https://openalex.org/W3005680577","https://openalex.org/W3020097842","https://openalex.org/W3029786391","https://openalex.org/W3110212018","https://openalex.org/W3113313164","https://openalex.org/W3118608800","https://openalex.org/W3135367836","https://openalex.org/W3177430934","https://openalex.org/W3204209514","https://openalex.org/W3211977733","https://openalex.org/W4205365495","https://openalex.org/W4211030719","https://openalex.org/W4392607758","https://openalex.org/W6636657728","https://openalex.org/W6684578312","https://openalex.org/W6783618930"],"related_works":["https://openalex.org/W3006513224","https://openalex.org/W2389214306","https://openalex.org/W2046456988","https://openalex.org/W2357409937","https://openalex.org/W2510582230","https://openalex.org/W2978674666","https://openalex.org/W2074430941","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W2955958993"],"abstract_inverted_index":{"Clustering":[0],"is":[1],"a":[2,7,13,38,98,104],"widely":[3],"used":[4,77],"technique":[5],"with":[6,54,66],"long":[8],"and":[9,103,121],"rich":[10],"history":[11],"in":[12,118],"variety":[14],"of":[15,33,93,101,113],"areas.":[16],"However,":[17],"most":[18],"existing":[19],"algorithms":[20],"do":[21],"not":[22],"scale":[23],"well":[24,49,125],"to":[25,126],"large":[26,99,127],"datasets,":[27],"or":[28],"are":[29],"missing":[30],"theoretical":[31,58],"guarantees":[32,59],"convergence.":[34],"This":[35],"paper":[36],"introduces":[37],"provably":[39],"robust":[40],"clustering":[41,97,116],"algorithm":[42,62,95,106,110],"based":[43],"on":[44,50,86],"loss":[45],"minimization":[46],"that":[47,60],"performs":[48],"Gaussian":[51],"mixture":[52],"models":[53],"outliers.":[55],"It":[56],"provides":[57],"the":[61,91,94,109,114],"obtains":[63],"high":[64,67],"accuracy":[65],"probability":[68],"under":[69],"certain":[70],"assumptions.":[71],"Moreover,":[72],"it":[73],"can":[74],"also":[75],"be":[76],"as":[78,130],"an":[79],"initialization":[80],"strategy":[81],"for":[82],"k-means":[83,105],"clustering.":[84],"Experiments":[85],"real-world":[87],"large-scale":[88],"datasets":[89,128],"demonstrate":[90],"effectiveness":[92],"when":[96],"number":[100],"clusters,":[102],"initialized":[107],"by":[108],"outperforms":[111],"many":[112],"classic":[115],"methods":[117],"both":[119],"speed":[120],"accuracy,":[122],"while":[123],"scaling":[124],"such":[129],"ImageNet.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}