{"id":"https://openalex.org/W7207617764","doi":"https://doi.org/10.48550/arxiv.2609.02304","title":"Bayes-Optimal BER and AUC: Estimation and Evaluation of Estimators","display_name":"Bayes-Optimal BER and AUC: Estimation and Evaluation of Estimators","publication_year":2026,"publication_date":"2026-09-02","ids":{"openalex":"https://openalex.org/W7207617764","doi":"https://doi.org/10.48550/arxiv.2609.02304"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.02304","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02304","pdf_url":"https://arxiv.org/pdf/2609.02304","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.02304","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5151748511","display_name":"Ryota Ushio","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ushio, Ryota","raw_affiliation_strings":["Graduate School of Frontier Sciences , The University of Tokyo , Tokyo , Japan","RIKEN AIP , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences , The University of Tokyo , Tokyo , Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"RIKEN AIP , Tokyo , Japan","institution_ids":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151843754","display_name":"Takashi Ishida","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ishida, Takashi","raw_affiliation_strings":["Graduate School of Frontier Sciences , The University of Tokyo , Tokyo , Japan","RIKEN AIP , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences , The University of Tokyo , Tokyo , Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"RIKEN AIP , Tokyo , Japan","institution_ids":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072744508","display_name":"Masashi Sugiyama","orcid":"https://orcid.org/0000-0001-6658-6743","observed_orcids":["https://orcid.org/0000-0001-6658-6743"]},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sugiyama, Masashi","raw_affiliation_strings":["Graduate School of Frontier Sciences , The University of Tokyo , Tokyo , Japan","RIKEN AIP , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences , The University of Tokyo , Tokyo , Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"RIKEN AIP , Tokyo , Japan","institution_ids":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.8359000086784363,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.8359000086784363,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.15389999747276306,"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":0.0035000001080334187,"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/soft-labels","display_name":"soft labels","score":0.9200000166893005},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.6690000295639038},{"id":"https://openalex.org/keywords/noisy-annotations","display_name":"noisy annotations","score":0.8709999918937683},{"id":"https://openalex.org/keywords/isotonic-regression","display_name":"isotonic regression","score":0.9190000295639038},{"id":"https://openalex.org/keywords/class-prior-estimation","display_name":"class prior estimation","score":0.7730000019073486},{"id":"https://openalex.org/keywords/finite-sample-error-bounds","display_name":"finite-sample error bounds","score":0.8820000290870667},{"id":"https://openalex.org/keywords/estimator-evaluation","display_name":"estimator evaluation","score":0.6320000290870667},{"id":"https://openalex.org/keywords/binary-classification","display_name":"binary classification","score":0.8040000200271606}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.8095999956130981},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6615999937057495},{"id":"https://openalex.org/C2780695315","wikidata":"https://www.wikidata.org/wiki/Q3799040","display_name":"Unobservable","level":2,"score":0.583299994468689},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5246999859809875},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5116999745368958},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3675999939441681},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3239000141620636},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.31529998779296875},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3147999942302704},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3093999922275543},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C39425265","wikidata":"https://www.wikidata.org/wiki/Q7098944","display_name":"Optimal estimation","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2614000141620636},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C133939421","wikidata":"https://www.wikidata.org/wiki/Q6865379","display_name":"Minimax estimator","level":4,"score":0.2540999948978424},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.02304","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02304","pdf_url":"https://arxiv.org/pdf/2609.02304","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.02304","doi":"https://doi.org/10.48550/arxiv.2609.02304","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.02304","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.02304","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02304","pdf_url":"https://arxiv.org/pdf/2609.02304","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7207617764.pdf","grobid_xml":"https://content.openalex.org/works/W7207617764.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W1876396543","https://openalex.org/W2218423201","https://openalex.org/W2972942550"],"related_works":["https://openalex.org/W4415036265","https://openalex.org/W3196347836","https://openalex.org/W4287018912","https://openalex.org/W4319999949","https://openalex.org/W4401693445","https://openalex.org/W4221152443","https://openalex.org/W2972942550","https://openalex.org/W6922570117","https://openalex.org/W2963972810","https://openalex.org/W7081961295"],"abstract_inverted_index":{"A":[0],"fundamental":[1],"quantity":[2,20],"in":[3,64,76,131,152],"machine":[4],"learning":[5],"is":[6,69,157,221,230],"the":[7,25,29,35,50,55,89,95,98,120,128,137,145,154,160,177,183,195,203,212,219,235,245,261,269,287,290],"optimal":[8,56,121,246,270],"performance":[9,75],"achievable":[10],"by":[11,166,173],"any":[12,227,266],"model":[13],"on":[14,223,280],"a":[15,32,71,148,199],"given":[16],"task.":[17],"Estimating":[18],"this":[19,107],"allows":[21],"us":[22,38],"to":[23,147,244,265],"distinguish":[24],"irreducible":[26],"part":[27],"of":[28,34,74,202,260,268],"error":[30,91,209],"from":[31,61],"deficiency":[33],"model,":[36],"telling":[37],"how":[39],"much":[40],"room":[41],"for":[42,119,211,240],"improvement":[43],"remains.":[44],"Recent":[45],"work":[46],"has":[47],"shown":[48],"that":[49],"Bayes":[51],"error,":[52],"or":[53,82,272],"equivalently":[54],"accuracy,":[57],"can":[58],"be":[59],"estimated":[60],"soft":[62,134,162,185],"labels":[63,135,163,186],"binary":[65],"classification.":[66],"However,":[67],"accuracy":[68],"often":[70],"poor":[72],"summary":[73],"settings":[77],"with":[78,109,190,198],"severe":[79],"class":[80,138,155,196],"imbalance":[81],"noisy":[83],"annotations,":[84],"where":[85],"metrics":[86],"such":[87,228],"as":[88],"balanced":[90],"rate":[92],"(BER)":[93],"and":[94,123,136,142,159,206,248,263,282,289],"area":[96],"under":[97],"ROC":[99],"curve":[100],"(AUC)":[101],"are":[102,140,164],"more":[103,149],"appropriate.":[104],"We":[105,115,125,233],"address":[106],"gap":[108],"two":[110],"complementary":[111],"contributions.":[112],"(i)":[113],"Estimation.":[114],"propose":[116],"soft-label-based":[117],"estimators":[118,146,288],"BER":[122,247,271],"AUC.":[124,249],"first":[126],"consider":[127],"clean":[129,184],"setting":[130,151],"which":[132,153],"true":[133],"prior":[139,156,197],"known,":[141],"then":[143],"extend":[144,234],"realistic":[150],"unknown":[158,168],"observed":[161],"corrupted":[165],"an":[167],"order-preserving":[169],"transformation,":[170],"possibly":[171],"followed":[172],"additive":[174],"noise.":[175],"In":[176],"latter":[178],"setting,":[179],"we":[180],"approximately":[181],"recover":[182],"via":[187],"isotonic":[188],"regression":[189],"auxiliary":[191],"hard":[192,204],"labels,":[193,205],"estimate":[194],"clipped":[200],"mean":[201],"derive":[207],"finite-sample":[208],"bounds":[210],"resulting":[213,251],"plug-in":[214],"estimators.":[215],"(ii)":[216],"Evaluation.":[217],"Since":[218],"optimum":[220],"unobservable":[222],"real":[224],"datasets,":[225],"evaluating":[226,241],"estimator":[229,267],"itself":[231],"nontrivial.":[232],"FeeBee":[236],"framework,":[237],"originally":[238],"proposed":[239,277],"Bayes-error":[242],"estimators,":[243],"The":[250],"procedure":[252],"provides":[253],"practical":[254],"evaluation":[255,291],"scores":[256],"without":[257],"requiring":[258],"knowledge":[259],"optimum,":[262],"applies":[264],"AUC,":[273],"not":[274],"only":[275],"our":[276],"ones.":[278],"Experiments":[279],"synthetic":[281],"real-world":[283],"datasets":[284],"validate":[285],"both":[286],"procedure.":[292]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-04T00:00:00"}