{"id":"https://openalex.org/W3113004165","doi":"https://doi.org/10.1145/3406325.3451131","title":"When is memorization of irrelevant training data necessary for high-accuracy learning?","display_name":"When is memorization of irrelevant training data necessary for high-accuracy learning?","publication_year":2021,"publication_date":"2021-06-15","ids":{"openalex":"https://openalex.org/W3113004165","doi":"https://doi.org/10.1145/3406325.3451131","mag":"3113004165"},"language":"en","primary_location":{"id":"doi:10.1145/3406325.3451131","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3406325.3451131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2012.06421","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gavin Brown","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gavin Brown","raw_affiliation_strings":["Boston University, USA"],"affiliations":[{"raw_affiliation_string":"Boston University, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mark Bun","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Bun","raw_affiliation_strings":["Boston University, USA"],"affiliations":[{"raw_affiliation_string":"Boston University, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Vitaly Feldman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vitaly Feldman","raw_affiliation_strings":["Apple, USA"],"affiliations":[{"raw_affiliation_string":"Apple, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Adam Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Smith","raw_affiliation_strings":["Boston University, USA"],"affiliations":[{"raw_affiliation_string":"Boston University, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kunal Talwar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunal Talwar","raw_affiliation_strings":["Apple, USA"],"affiliations":[{"raw_affiliation_string":"Apple, USA","institution_ids":["https://openalex.org/I4210153776"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I111088046"],"apc_list":null,"apc_paid":null,"fwci":2.7992,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.91803451,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9987000226974487,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9987000226974487,"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":0.998199999332428,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.994700014591217,"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/memorization","display_name":"Memorization","score":0.8562999963760376},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5845000147819519},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.5756000280380249},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5210000276565552},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5145000219345093},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.45590001344680786},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3862000107765198}],"concepts":[{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.8562999963760376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6241999864578247},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5845000147819519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5774999856948853},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.5756000280380249},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5210000276565552},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5145000219345093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4966000020503998},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26260000467300415}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3406325.3451131","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3406325.3451131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2012.06421","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.06421","pdf_url":"https://arxiv.org/pdf/2012.06421","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"},{"id":"pmh:oai:null:2144/43230","is_oa":false,"landing_page_url":"https://arxiv.org/abs/2012.06421","pdf_url":null,"source":{"id":"https://openalex.org/S4306402384","display_name":"OpenBU (Boston University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I111088046","host_organization_name":"Boston University","host_organization_lineage":["https://openalex.org/I111088046"],"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":"Conference materials"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2012.06421","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.06421","pdf_url":"https://arxiv.org/pdf/2012.06421","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7291535841","display_name":null,"funder_award_id":"CF-1763786, CCF-1947889","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1873763122","https://openalex.org/W1992926795","https://openalex.org/W2010523825","https://openalex.org/W2034603029","https://openalex.org/W2107917944","https://openalex.org/W2110868467","https://openalex.org/W2245160765","https://openalex.org/W2520881573","https://openalex.org/W2535690855","https://openalex.org/W2898996243","https://openalex.org/W2903586563","https://openalex.org/W2962750290","https://openalex.org/W2963356344","https://openalex.org/W2963359984","https://openalex.org/W2963384289","https://openalex.org/W2963699739","https://openalex.org/W2964184826","https://openalex.org/W2982531080","https://openalex.org/W3035261884","https://openalex.org/W3048045781","https://openalex.org/W6780309617"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"machine":[1],"learning":[2],"models":[3,20,132],"are":[4,92],"complex":[5,19],"and":[6,94,103],"frequently":[7],"encode":[8],"surprising":[9],"amounts":[10],"of":[11,48,81,107,131],"information":[12,30,76,109],"about":[13,77],"individual":[14],"inputs.":[15],"In":[16,38],"extreme":[17],"cases,":[18],"appear":[21],"to":[22,43,113],"memorize":[23],"entire":[24],"input":[25],"examples,":[26],"including":[27],"seemingly":[28],"irrelevant":[29,112],"(social":[31],"security":[32],"numbers":[33],"from":[34],"text,":[35],"for":[36,52,134],"example).":[37],"this":[39,46],"paper,":[40],"we":[41],"aim":[42],"understand":[44],"whether":[45],"sort":[47],"memorization":[49],"is":[50,110],"necessary":[51],"accurate":[53,64],"learning.":[54,135],"We":[55],"describe":[56],"natural":[57],"prediction":[58,71],"problems":[59],"in":[60,69],"which":[61],"every":[62],"sufficiently":[63],"training":[65,83,126],"algorithm":[66,127],"must":[67],"encode,":[68],"the":[70,75,90,100,114,125,129],"model,":[72],"essentially":[73],"all":[74],"a":[78],"large":[79],"subset":[80],"its":[82],"examples.":[84],"This":[85],"remains":[86],"true":[87],"even":[88,104],"when":[89,105],"examples":[91],"high-dimensional":[93],"have":[95],"entropy":[96],"much":[97],"higher":[98],"than":[99],"sample":[101],"size,":[102],"most":[106],"that":[108],"ultimately":[111],"task":[115],"at":[116],"hand.":[117],"Further,":[118],"our":[119],"results":[120],"do":[121],"not":[122],"depend":[123],"on":[124],"or":[128],"class":[130],"used":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2020-12-21T00:00:00"}