{"id":"https://openalex.org/W3099518927","doi":"https://doi.org/10.1109/icassp39728.2021.9413946","title":"Benign Overfitting in Binary Classification of Gaussian Mixtures","display_name":"Benign Overfitting in Binary Classification of Gaussian Mixtures","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3099518927","doi":"https://doi.org/10.1109/icassp39728.2021.9413946","mag":"3099518927"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/2011.09148v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090879904","display_name":"Ke Wang","orcid":"https://orcid.org/0000-0001-5951-1727"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Wang","raw_affiliation_strings":["University of California, Santa Barbara","University of California,Department of Statistics and Applied Probability,Santa Barbara"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"University of California,Department of Statistics and Applied Probability,Santa Barbara","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024812488","display_name":"Christos Thrampoulidis","orcid":"https://orcid.org/0000-0001-9053-9365"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Christos Thrampoulidis","raw_affiliation_strings":["University of British Columbia, Vancouver","University of British Columbia,Department of Electrical and Computer Engineering,Vancouver"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"University of British Columbia,Department of Electrical and Computer Engineering,Vancouver","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5861,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65837579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4030","last_page":"4034"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9965000152587891,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9965000152587891,"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":0.9926000237464905,"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/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/1602","display_name":"Analytical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.9869216680526733},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.689601480960846},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.6366918087005615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6175304055213928},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6067253351211548},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5921429395675659},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5907637476921082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5372042655944824},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42605364322662354},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.42466315627098083},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4108033776283264},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34965962171554565}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9869216680526733},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.689601480960846},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.6366918087005615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6175304055213928},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6067253351211548},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5921429395675659},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5907637476921082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5372042655944824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42605364322662354},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.42466315627098083},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4108033776283264},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34965962171554565},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"mag:3099518927","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2011.09148v1","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,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.17023/7356-jq12","is_oa":true,"landing_page_url":"https://doi.org/10.17023/7356-jq12","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"mag:3099518927","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2011.09148v1","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,"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":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2550848904","https://openalex.org/W2963017107","https://openalex.org/W3014316192","https://openalex.org/W3018252856","https://openalex.org/W3080936353","https://openalex.org/W6623408330","https://openalex.org/W6683595889","https://openalex.org/W6745276634","https://openalex.org/W6752127812","https://openalex.org/W6757899452","https://openalex.org/W6760498417","https://openalex.org/W6766887723","https://openalex.org/W6767329639","https://openalex.org/W6767403159","https://openalex.org/W6769472860","https://openalex.org/W6771471661","https://openalex.org/W6774616501","https://openalex.org/W6775081096","https://openalex.org/W6776071938","https://openalex.org/W6777730395","https://openalex.org/W6779502704","https://openalex.org/W6783911279","https://openalex.org/W6784388680","https://openalex.org/W6784796196","https://openalex.org/W6785903974","https://openalex.org/W6786743562"],"related_works":["https://openalex.org/W3162172987","https://openalex.org/W3025991882","https://openalex.org/W3018252856","https://openalex.org/W2147965230","https://openalex.org/W2619902386","https://openalex.org/W2947548407","https://openalex.org/W2088622335","https://openalex.org/W2316257015","https://openalex.org/W3207279771","https://openalex.org/W2093183893","https://openalex.org/W245192467","https://openalex.org/W2950340191","https://openalex.org/W3094227124","https://openalex.org/W2132141292","https://openalex.org/W2964291083","https://openalex.org/W3160732325","https://openalex.org/W3201156294","https://openalex.org/W2037679392","https://openalex.org/W2606510888","https://openalex.org/W2902741866"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"generalize":[3],"well":[4,23],"despite":[5],"being":[6],"exceedingly":[7],"overparameterized,":[8],"but":[9],"understanding":[10,32],"the":[11,84,88,99,106,112,116],"statistical":[12],"principles":[13],"behind":[14],"this":[15],"so":[16],"called":[17],"benign-overfitting":[18,33,50],"phenomenon":[19],"is":[20],"not":[21],"yet":[22],"understood.":[24],"Recently":[25],"there":[26],"has":[27,71],"been":[28],"remarkable":[29],"progress":[30],"towards":[31],"in":[34,80],"simpler":[35],"models,":[36],"such":[37],"as":[38],"linear":[39,45],"regression":[40],"and,":[41],"even":[42],"more":[43],"recently,":[44],"classification.":[46],"This":[47],"paper":[48],"studies":[49],"for":[51],"data":[52],"generated":[53],"from":[54],"a":[55],"popular":[56],"binary":[57],"Gaussian":[58],"mixtures":[59],"model":[60],"(GMM)":[61],"and":[62,115],"classifiers":[63],"trained":[64],"by":[65],"support-vector":[66],"machines":[67],"(SVM).":[68],"Our":[69],"approach":[70],"two":[72,107],"steps.":[73],"First,":[74],"we":[75,93],"leverage":[76],"an":[77],"idea":[78],"introduced":[79],"[2]":[81],"to":[82,87,121],"relate":[83],"SVM":[85],"solution":[86],"least-squares":[89],"(LS)":[90],"solution.":[91,104],"Second,":[92],"derive":[94],"novel":[95],"non-asymptotic":[96],"bounds":[97],"on":[98,111],"classification":[100],"error":[101],"of":[102],"LS":[103],"Combining":[105],"gives":[108],"sufficient":[109],"conditions":[110],"overparameterization":[113],"ratio":[114,118],"signal-to-noise":[117],"that":[119],"lead":[120],"benign":[122],"overfitting.":[123],"We":[124],"corroborate":[125],"our":[126],"theoretical":[127],"findings":[128],"with":[129],"numerical":[130],"simulations.":[131]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}