{"id":"https://openalex.org/W2922153390","doi":"https://doi.org/10.1137/20m1336072","title":"Two Models of Double Descent for Weak Features","display_name":"Two Models of Double Descent for Weak Features","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W2922153390","doi":"https://doi.org/10.1137/20m1336072","mag":"2922153390"},"language":"en","primary_location":{"id":"doi:10.1137/20m1336072","is_oa":true,"landing_page_url":"https://doi.org/10.1137/20m1336072","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/20M1336072","source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://epubs.siam.org/doi/pdf/10.1137/20M1336072","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mikhail Belkin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mikhail Belkin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Daniel Hsu","orcid":"https://orcid.org/0000-0002-3495-7113"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Hsu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Ji Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji Xu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.2187,"has_fulltext":true,"cited_by_count":122,"citation_normalized_percentile":{"value":0.99384377,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"2","issue":"4","first_page":"1167","last_page":"1180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.364300012588501,"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"}},"topics":[{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.364300012588501,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.13670000433921814,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.060600001364946365,"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/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.6305999755859375},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.47859999537467957},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.47200000286102295},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4300999939441681},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38749998807907104},{"id":"https://openalex.org/keywords/curve-fitting","display_name":"Curve fitting","score":0.3846000134944916},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.36309999227523804},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3621000051498413}],"concepts":[{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6305999755859375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5737000107765198},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.47859999537467957},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.47200000286102295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44020000100135803},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4300999939441681},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4153999984264374},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C184389593","wikidata":"https://www.wikidata.org/wiki/Q603159","display_name":"Curve fitting","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3449999988079071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.33550000190734863},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C119247159","wikidata":"https://www.wikidata.org/wiki/Q1366192","display_name":"System identification","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1137/20m1336072","is_oa":true,"landing_page_url":"https://doi.org/10.1137/20m1336072","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/20M1336072","source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1903.07571","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.07571","pdf_url":"https://arxiv.org/pdf/1903.07571","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1137/20m1336072","is_oa":true,"landing_page_url":"https://doi.org/10.1137/20m1336072","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/20M1336072","source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1302751805","display_name":"RI: Small: Learning discrete structure from continuous spaces","funder_award_id":"1815697","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3974885098","display_name":null,"funder_award_id":"1740833","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4786009209","display_name":null,"funder_award_id":"CCF-1740833","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5127838929","display_name":null,"funder_award_id":"IIS-1815697","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6894402473","display_name":null,"funder_award_id":"Fellowship","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/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320309374","display_name":"Ohio State University","ror":"https://ror.org/00rs6vg23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2922153390.pdf","grobid_xml":"https://content.openalex.org/works/W2922153390.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1964862779","https://openalex.org/W1992774725","https://openalex.org/W1993146053","https://openalex.org/W2003202757","https://openalex.org/W2044148561","https://openalex.org/W2059825003","https://openalex.org/W2068558570","https://openalex.org/W2088658556","https://openalex.org/W2150872430","https://openalex.org/W2163855617","https://openalex.org/W2168494960","https://openalex.org/W2896549049","https://openalex.org/W2963518130","https://openalex.org/W3014316192","https://openalex.org/W3021058579"],"related_works":[],"abstract_inverted_index":{"The":[0],"\u201cdouble":[1],"descent\u201d":[2],"risk":[3,50,69],"curve":[4,32],"was":[5],"proposed":[6],"to":[7,60],"qualitatively":[8],"describe":[9],"the":[10,28,39,49,53,61,68],"out-of-sample":[11],"prediction":[12],"accuracy":[13],"of":[14,30,55,99],"variably":[15],"parameterized":[16],"machine":[17],"learning":[18],"models.":[19],"This":[20,80],"article":[21],"provides":[22],"a":[23,107],"precise":[24],"mathematical":[25],"analysis":[26],"for":[27],"shape":[29],"this":[31],"in":[33,87,105],"two":[34],"simple":[35],"data":[36],"models":[37,101],"with":[38,97],"least":[40],"squares/least":[41],"norm":[42],"predictor.":[43],"Specifically,":[44],"it":[45],"is":[46,58,95],"shown":[47],"that":[48,67,98,102],"peaks":[51],"when":[52],"number":[54],"features":[56,104],"$p$":[57,76],"close":[59],"sample":[62],"size":[63],"$n$":[64],"but":[65],"also":[66],"sometimes":[70],"decreases":[71],"toward":[72],"its":[73],"minimum":[74],"as":[75],"increases":[77],"beyond":[78],"$n$.":[79],"behavior":[81],"parallels":[82],"some":[83],"key":[84],"patterns":[85],"observed":[86],"large":[88],"models,":[89],"including":[90],"modern":[91],"neural":[92],"networks,":[93],"and":[94],"contrasted":[96],"\u201cprescient\u201d":[100],"select":[103],"an":[106],"priori":[108],"optimal":[109],"order.":[110]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":30},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":14}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2019-03-22T00:00:00"}