{"id":"https://openalex.org/W7223395973","doi":"https://doi.org/10.48550/arxiv.2610.31603","title":"Is Spectral Self-Supervised Learning a Minimax Optimal Method of Density Ratio Estimation?","display_name":"Is Spectral Self-Supervised Learning a Minimax Optimal Method of Density Ratio Estimation?","publication_year":2026,"publication_date":"2026-10-22","ids":{"openalex":"https://openalex.org/W7223395973","doi":"https://doi.org/10.48550/arxiv.2610.31603"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.31603","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.31603","pdf_url":"https://arxiv.org/pdf/2610.31603","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"},"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/2610.31603","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033630219","display_name":"Hiroki Waida","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":"JP","type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Waida, Hiroki","raw_affiliation_strings":["Department of Mathematical and Computing Science , Institute of Science Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematical and Computing Science , Institute of Science Tokyo , Japan","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088569462","display_name":"Takafumi Kanamori","orcid":"https://orcid.org/0000-0001-6878-5850","observed_orcids":["https://orcid.org/0000-0001-6878-5850"]},"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/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":"JP","type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kanamori, Takafumi","raw_affiliation_strings":["Department of Mathematical and Computing Science , Institute of Science Tokyo , Japan","RIKEN AIP , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematical and Computing Science , Institute of Science Tokyo , Japan","institution_ids":["https://openalex.org/I4400009020"]},{"raw_affiliation_string":"RIKEN AIP , 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":0,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.6333000063896179,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.6333000063896179,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.14499999582767487,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.04879999905824661,"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/density-ratio-estimation","display_name":"density ratio estimation","score":0.9990000128746033},{"id":"https://openalex.org/keywords/minimax-optimality","display_name":"minimax optimality","score":0.968999981880188},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.843999981880188},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.8629999756813049},{"id":"https://openalex.org/keywords/self-supervised-representation-learning","display_name":"self-supervised representation learning","score":0.8330000042915344},{"id":"https://openalex.org/keywords/joint-density-estimation","display_name":"joint density estimation","score":0.5099999904632568}],"concepts":[{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.9110999703407288},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7351999878883362},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.7294999957084656},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6801000237464905},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5584999918937683},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5210000276565552},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5072000026702881},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.47780001163482666},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4481000006198883},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42739999294281006},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C133939421","wikidata":"https://www.wikidata.org/wiki/Q6865379","display_name":"Minimax estimator","level":4,"score":0.3287999927997589},{"id":"https://openalex.org/C117148685","wikidata":"https://www.wikidata.org/wiki/Q6865376","display_name":"Minimax approximation algorithm","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C2779915298","wikidata":"https://www.wikidata.org/wiki/Q7604400","display_name":"Statistical learning theory","level":3,"score":0.2939999997615814},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C157709441","wikidata":"https://www.wikidata.org/wiki/Q1411887","display_name":"Uniform convergence","level":3,"score":0.2646999955177307}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.31603","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.31603","pdf_url":"https://arxiv.org/pdf/2610.31603","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.2610.31603","doi":"https://doi.org/10.48550/arxiv.2610.31603","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.31603","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.31603","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.31603","pdf_url":"https://arxiv.org/pdf/2610.31603","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":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223395973.pdf","grobid_xml":"https://content.openalex.org/works/W7223395973.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W4297808394","https://openalex.org/W4307928437","https://openalex.org/W6960139023","https://openalex.org/W7102398897"],"related_works":["https://openalex.org/W7033996086","https://openalex.org/W4392090196","https://openalex.org/W4385473876","https://openalex.org/W7167789153","https://openalex.org/W243488030","https://openalex.org/W7213371008","https://openalex.org/W1970387193","https://openalex.org/W7165552905","https://openalex.org/W3036122622","https://openalex.org/W7211904141"],"abstract_inverted_index":{"Spectral":[0],"self-supervised":[1,98,117,170],"learning":[2,118],"is":[3,55],"a":[4,139,158],"method":[5,28],"of":[6,22,35,51,71,81,97,108],"density":[7,21,82,111,171],"ratio":[8,83,172],"estimation":[9,84],"for":[10,105,135,169],"the":[11,19,23,36,66,69,72,78,95,124,164],"setting":[12],"in":[13,33,94,157],"which":[14],"only":[15],"samples":[16],"drawn":[17],"from":[18],"joint":[20],"numerator":[24],"are":[25,114,149],"available.":[26],"The":[27],"has":[29],"extensively":[30],"been":[31,92],"studied":[32],"terms":[34],"computational":[37],"properties,":[38],"such":[39],"as":[40],"optimal":[41,152],"solutions":[42],"and":[43,77],"connections":[44],"to":[45,74,128,154],"representation":[46,99],"learning.":[47,100],"However,":[48],"theoretical":[49],"understanding":[50],"its":[52],"statistical":[53,79],"property":[54],"still":[56],"insufficient.":[57],"In":[58],"this":[59],"work,":[60],"we":[61,143],"study":[62],"three":[63],"questions,":[64],"namely,":[65],"minimax":[67,125,151],"optimality,":[68,126],"applicability":[70],"theory":[73],"regularized":[75,115],"algorithms,":[76],"merits":[80],"with":[85,138],"data":[86,140],"augmentation":[87,141],"mechanisms":[88],"that":[89,104,120,134,148],"have":[90],"recently":[91],"considered":[93],"context":[96],"We":[101,131,161],"first":[102],"show":[103],"general":[106],"classes":[107],"H\u00f6lder":[109],"continuous":[110],"ratios,":[112],"there":[113],"spectral":[116],"algorithms":[119],"yield":[121],"estimators":[122],"attaining":[123],"up":[127],"logarithmic":[129,155],"factors.":[130],"then":[132],"prove":[133],"subclasses":[136],"endowed":[137],"mechanism,":[142],"obtain":[144],"faster":[145],"convergence":[146],"rates":[147],"also":[150,162],"(up":[153],"factors)":[156],"weaker":[159],"sense.":[160],"present":[163],"key":[165],"proof":[166],"ideas":[167],"tailored":[168],"estimation.":[173]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-24T00:00:00"}