{"id":"https://openalex.org/W2962960950","doi":"https://doi.org/10.48550/arxiv.1312.1054","title":"Faster and Sample Near-Optimal Algorithms for Proper Learning Mixtures of Gaussians","display_name":"Faster and Sample Near-Optimal Algorithms for Proper Learning Mixtures of Gaussians","alternate_titles":[],"publication_year":2013,"publication_date":"2013-12-04","ids":{"openalex":"https://openalex.org/W2962960950","doi":"https://doi.org/10.48550/arxiv.1312.1054","mag":"2962960950"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1312.1054","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1312.1054","pdf_url":"https://arxiv.org/pdf/1312.1054","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W2962960950"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1312.1054","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034822411","display_name":"Constantinos Daskalakis","orcid":"https://orcid.org/0000-0002-5451-0490","observed_orcids":["https://orcid.org/0000-0002-5451-0490"]},"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,"contributor_roles":[],"raw_author_name":"Daskalakis, Constantinos","raw_affiliation_strings":["EECS , MIT","Massachusetts Institute of Technology, Cambridge, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EECS , MIT","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047778197","display_name":"Gautam Kamath","orcid":"https://orcid.org/0000-0003-0048-2559","observed_orcids":["https://orcid.org/0000-0003-0048-2559"]},"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,"contributor_roles":[],"raw_author_name":"Kamath, Gautam","raw_affiliation_strings":["EECS , MIT","Massachusetts Institute of Technology, Cambridge, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EECS , MIT","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":82,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1183","last_page":"1213"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.7470999956130981,"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":0.7470999956130981,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.17350000143051147,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.010099999606609344,"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/proper-learning","display_name":"proper learning","score":0.7720000147819519},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"sample complexity","score":0.8510000109672546},{"id":"https://openalex.org/keywords/total-variation-distance","display_name":"total variation distance","score":0.8309999704360962},{"id":"https://openalex.org/keywords/hypothesis-selection","display_name":"hypothesis selection","score":0.9359999895095825},{"id":"https://openalex.org/keywords/chemical-separation","display_name":"chemical separation","score":0.3190000057220459},{"id":"https://openalex.org/keywords/computational-learning-theory","display_name":"computational learning theory","score":0.33899998664855957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6252023577690125},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5666216611862183},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5609449148178101},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5505924820899963},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5400233268737793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3666938245296478},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09575822949409485},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:arXiv.org:1312.1054","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1312.1054","pdf_url":"https://arxiv.org/pdf/1312.1054","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1312.1054","doi":"https://doi.org/10.48550/arxiv.1312.1054","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1312.1054","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2962960950","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v35/daskalakis14.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418075","display_name":"Conference on Learning Theory","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Conference on Learning Theory","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.649.7965","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.649.7965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://jmlr.org/proceedings/papers/v35/daskalakis14.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.748.1142","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.748.1142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1312.1054.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1312.1054","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1312.1054","pdf_url":"https://arxiv.org/pdf/1312.1054","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6715213848","display_name":"CAREER: Towards a Constructive Theory of Networked Interactions","funder_award_id":"0953960","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7461983665","display_name":"ICES: Small: A Probabilistic Look at Algorithmic Game Theory","funder_award_id":"1101491","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"},{"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/W2962960950.pdf","grobid_xml":"https://content.openalex.org/works/W2962960950.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1574816920","https://openalex.org/W1585566614","https://openalex.org/W1763164889","https://openalex.org/W1796325169","https://openalex.org/W1956647075","https://openalex.org/W1965612527","https://openalex.org/W1969015668","https://openalex.org/W1974088667","https://openalex.org/W1988645907","https://openalex.org/W2012828271","https://openalex.org/W2014565165","https://openalex.org/W2025460138","https://openalex.org/W2025533349","https://openalex.org/W2026302946","https://openalex.org/W2032916024","https://openalex.org/W2038147876","https://openalex.org/W2047471939","https://openalex.org/W2049633694","https://openalex.org/W2063178190","https://openalex.org/W2063218326","https://openalex.org/W2069713581","https://openalex.org/W2079234446","https://openalex.org/W2095374884","https://openalex.org/W2122170585","https://openalex.org/W2143122862","https://openalex.org/W2146756121","https://openalex.org/W2177772290","https://openalex.org/W2949977662","https://openalex.org/W2952995770"],"related_works":["https://openalex.org/W1779289138","https://openalex.org/W2892884340","https://openalex.org/W2952131701","https://openalex.org/W1956647075","https://openalex.org/W2026302946","https://openalex.org/W2788738055","https://openalex.org/W7097980922","https://openalex.org/W2146756121","https://openalex.org/W7098777575","https://openalex.org/W7099279252"],"abstract_inverted_index":{"We":[0],"provide":[1],"an":[2,20,87,118],"algorithm":[3,24,56,68,91,122,133,183],"for":[4,92,175],"properly":[5],"learning":[6],"mixtures":[7],"of":[8,82,106,160,172,178],"two":[9],"single-dimensional":[10],"Gaussians":[11],"without":[12],"any":[13,188],"separability":[14],"assumptions.":[15],"Given":[16,168],"$\\tilde{O}(1/\\varepsilon^2)$":[17],"samples":[18,136],"from":[19,98,137,156],"unknown":[21,119,139],"mixture,":[22],"our":[23,83,121,181],"outputs":[25,123],"a":[26,58,94,104,124,157],"mixture":[27,73],"that":[28,114],"is":[29,41,86,115,127],"$\\varepsilon$-close":[30,116],"in":[31,35,78],"total":[32],"variation":[33],"distance,":[34],"time":[36,163],"$\\tilde{O}(1/\\varepsilon^5)$.":[37],"Our":[38],"sample":[39],"complexity":[40],"optimal":[42],"up":[43],"to":[44,117,129,166,187],"logarithmic":[45],"factors,":[46],"and":[47,63,75,89,141],"significantly":[48],"improves":[49,147],"upon":[50],"both":[51],"Kalai":[52],"et":[53,65],"al.,":[54,66],"whose":[55,67],"has":[57],"prohibitive":[59],"dependence":[60,159],"on":[61,71,164],"$1/\\varepsilon$,":[62],"Feldman":[64],"requires":[69,134],"bounds":[70],"the":[72,130,138,153,161,169,176],"parameters":[74],"depends":[76],"pseudo-polynomially":[77],"these":[79],"parameters.":[80],"One":[81],"main":[84],"contributions":[85],"improved":[88,182],"generalized":[90],"selecting":[93],"good":[95],"candidate":[96,113,125],"distribution":[97,140],"among":[99],"competing":[100],"hypotheses.":[101],"Namely,":[102],"given":[103],"collection":[105],"$N$":[107,165],"hypotheses":[108],"containing":[109],"at":[110],"least":[111],"one":[112],"distribution,":[120],"which":[126,146],"$O(\\varepsilon)$-close":[128],"distribution.":[131],"The":[132],"${O}(\\log{N}/\\varepsilon^2)$":[135],"${O}(N":[142],"\\log":[143],"N/\\varepsilon^2)$":[144],"time,":[145],"previous":[148],"such":[149,173,189],"results":[150,174],"(such":[151],"as":[152],"Scheff\u00e9":[154],"estimator)":[155],"quadratic":[158],"running":[162],"quasilinear.":[167],"wide":[170],"use":[171],"purpose":[177],"hypothesis":[179],"selection,":[180],"implies":[184],"immediate":[185],"improvements":[186],"use.":[190]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2962960950","counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2019-07-30T00:00:00"}
