{"id":"https://openalex.org/W3217628683","doi":"https://doi.org/10.1145/3519935.3520012","title":"Clustering mixtures with almost optimal separation in polynomial time","display_name":"Clustering mixtures with almost optimal separation in polynomial time","publication_year":2022,"publication_date":"2022-06-09","ids":{"openalex":"https://openalex.org/W3217628683","doi":"https://doi.org/10.1145/3519935.3520012","mag":"3217628683"},"language":"en","primary_location":{"id":"doi:10.1145/3519935.3520012","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3519935.3520012","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3519935.3520012","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual ACM SIGACT Symposium on Theory of Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3519935.3520012","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102433376","display_name":"Allen Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allen Liu","raw_affiliation_strings":["Massachusetts Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101439736","display_name":"Jerry Li","orcid":"https://orcid.org/0000-0002-8774-826X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jerry Li","raw_affiliation_strings":["Microsoft Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1687,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.35587849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"8","issue":null,"first_page":"1248","last_page":"1261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9993000030517578,"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":0.9993000030517578,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9966999888420105,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9948999881744385,"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":0.845862865447998},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.5872442722320557},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5871270298957825},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.5645915865898132},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5492135286331177},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5338355898857117},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.4779784083366394},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.4689238667488098},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4501311182975769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3325667381286621},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12688812613487244}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.845862865447998},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.5872442722320557},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5871270298957825},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.5645915865898132},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5492135286331177},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5338355898857117},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.4779784083366394},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.4689238667488098},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4501311182975769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3325667381286621},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12688812613487244},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3519935.3520012","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3519935.3520012","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3519935.3520012","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual ACM SIGACT Symposium on Theory of Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/146433","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/146433","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM|Proceedings of the 54th Annual ACM SIGACT Symposium on Theory of Computing","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"doi:10.1145/3519935.3520012","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3519935.3520012","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3519935.3520012","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual ACM SIGACT Symposium on Theory of Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3217628683.pdf","grobid_xml":"https://content.openalex.org/works/W3217628683.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1574816920","https://openalex.org/W1585566614","https://openalex.org/W1956647075","https://openalex.org/W1980018091","https://openalex.org/W1985792472","https://openalex.org/W2010072035","https://openalex.org/W2012828271","https://openalex.org/W2014565165","https://openalex.org/W2022852240","https://openalex.org/W2026302946","https://openalex.org/W2047064469","https://openalex.org/W2053742104","https://openalex.org/W2057214765","https://openalex.org/W2059971059","https://openalex.org/W2062817469","https://openalex.org/W2137854958","https://openalex.org/W2143122862","https://openalex.org/W2146758737","https://openalex.org/W2161185760","https://openalex.org/W2177772290","https://openalex.org/W2290522125","https://openalex.org/W2345432430","https://openalex.org/W2740889500","https://openalex.org/W2808754399","https://openalex.org/W2885790188","https://openalex.org/W2891786606","https://openalex.org/W2911495555","https://openalex.org/W2962820675","https://openalex.org/W2962907923","https://openalex.org/W2962960950","https://openalex.org/W2963496884","https://openalex.org/W2963558956","https://openalex.org/W2963626260","https://openalex.org/W2963658177","https://openalex.org/W2963800155","https://openalex.org/W2964044021","https://openalex.org/W2964073168","https://openalex.org/W2964164735","https://openalex.org/W2964234624","https://openalex.org/W2964288084","https://openalex.org/W2964317125","https://openalex.org/W2966353252","https://openalex.org/W2984272935","https://openalex.org/W3020097842","https://openalex.org/W3084623378","https://openalex.org/W3116934360","https://openalex.org/W3117289910","https://openalex.org/W3127363723","https://openalex.org/W3138914377","https://openalex.org/W3171084445","https://openalex.org/W4205818646"],"related_works":["https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W1975321310","https://openalex.org/W2287611352","https://openalex.org/W1952261593","https://openalex.org/W2014494654","https://openalex.org/W320684304","https://openalex.org/W1509352139","https://openalex.org/W2990323019","https://openalex.org/W1774334694"],"abstract_inverted_index":{"We":[0,13,98,182],"consider":[1],"the":[2,27,48,53,90,100,138,164,196],"problem":[3,162],"of":[4,7,20,35,57,189,191],"clustering":[5,56,78],"mixtures":[6,188],"mean-separated":[8],"Gaussians":[9],"in":[10,105,168],"high":[11],"dimensions.":[12],"are":[14,96],"given":[15],"samples":[16,124],"from":[17],"a":[18,76,132,192],"mixture":[19],"k":[21],"identity":[22],"covariance":[23],"Gaussians,":[24],"so":[25,135],"that":[26,63],"minimum":[28],"pairwise":[29],"distance":[30],"between":[31],"any":[32,149],"two":[33],"pairs":[34],"means":[36],"is":[37,50,61,69,140],"at":[38,85],"least":[39,86],"\u0394,":[40],"for":[41,148,160],"some":[42],"parameter":[43],"\u0394":[44,65,141],">":[45,151],"0,":[46],"and":[47,72,108,125,127,170],"goal":[49],"to":[51,74,187],"recover":[52,75,131],"ground":[54],"truth":[55],"these":[58],"samples.":[59],"It":[60],"folklore":[62],"separation":[64,139,165,178],"=":[66,142],"\u0398":[67],"(\u221alogk)":[68],"both":[70],"necessary":[71],"sufficient":[73],"good":[77,133],"(say":[79],"with":[80],"constant":[81],"or":[82],"1/poly(k)":[83],"error),":[84],"information":[87],"theoretically.":[88],"However,":[89],"estimators":[91],"which":[92,103,109,120,128,173,194],"achieve":[93],"this":[94,112,161],"guarantee":[95],"inefficient.":[97],"give":[99,117],"first":[101],"algorithm":[102,119],"runs":[104],"polynomial":[106,154,167],"time,":[107,126],"almost":[110],"matches":[111],"guarantee.":[113],"More":[114],"precisely,":[115],"we":[116],"an":[118],"takes":[121],"polynomially":[122],"many":[123],"can":[129],"successfully":[130],"clustering,":[134],"long":[136],"as":[137],"\u03a9":[143],"(log1/2":[144],"+":[145],"c":[146,150],"k),":[147],"0.":[152],"Previously,":[153],"time":[155],"algorithms":[156,172],"were":[157],"only":[158],"known":[159],"when":[163],"was":[166],"k,":[169],"all":[171],"could":[174],"tolerate":[175],"poly":[176],"logk":[177],"required":[179],"quasipolynomial":[180],"time.":[181],"also":[183],"extend":[184],"our":[185],"result":[186],"translations":[190],"distribution":[193],"satisfies":[195],"Poincar\u00e9":[197],"inequality,":[198],"under":[199],"additional":[200],"mild":[201],"assumptions.":[202]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}