{"id":"https://openalex.org/W7160824593","doi":"https://doi.org/10.48550/arxiv.2605.07808","title":"The Minimax Rate of Second-Order Calibration","display_name":"The Minimax Rate of Second-Order Calibration","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160824593","doi":"https://doi.org/10.48550/arxiv.2605.07808"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.07808","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07808","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.07808","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043239539","display_name":"Kamil Ciosek","orcid":"https://orcid.org/0000-0002-0238-9393"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ciosek, Kamil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083856371","display_name":"Banafsheh Rafiee","orcid":"https://orcid.org/0000-0003-4641-7349"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rafiee, Banafsheh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024789936","display_name":"Sina Ghiassian","orcid":"https://orcid.org/0000-0001-5853-5049"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghiassian, Sina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047511363","display_name":"Nicol\u00f2 Felicioni","orcid":"https://orcid.org/0000-0002-3555-7760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felicioni, Nicol\u00f2","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.2282000035047531,"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":0.2282000035047531,"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":0.18019999563694,"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":0.17630000412464142,"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/minimax","display_name":"Minimax","score":0.8528000116348267},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6223000288009644},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.5989000201225281},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.5501999855041504},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.42320001125335693},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.39590001106262207},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.37770000100135803},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.36649999022483826}],"concepts":[{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.8528000116348267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7035999894142151},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6223000288009644},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.5989000201225281},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.5501999855041504},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4749999940395355},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.34119999408721924},{"id":"https://openalex.org/C120068334","wikidata":"https://www.wikidata.org/wiki/Q45343","display_name":"Polynomial regression","level":3,"score":0.3337000012397766},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29739999771118164},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C21430997","wikidata":"https://www.wikidata.org/wiki/Q5159279","display_name":"Conditional variance","level":4,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.07808","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07808","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.07808","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07808","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"characterize":[1],"the":[2,7,23,27,39,67,80,106,121,125,133,148,159,163,166],"minimax":[3,95],"rate":[4,71,82,161],"of":[5,26,49,60,128,140,151,165],"estimating":[6],"second-order":[8,111,141],"calibration":[9,50,68,142],"error":[10,69],"for":[11,110],"binary":[12],"classification,":[13],"which":[14],"quantifies":[15],"whether":[16],"a":[17,58,76,102,115,137],"higher-order":[18,130],"predictor's":[19],"epistemic-uncertainty":[20],"estimate":[21,127],"matches":[22],"conditional":[24],"variance":[25],"label":[28],"probability":[29],"on":[30],"its":[31],"level":[32],"sets.":[33],"Our":[34,156],"key":[35],"observation":[36],"is":[37],"that":[38,118],"sech":[40],"perturbation":[41],"kernel,":[42],"previously":[43],"used":[44],"only":[45],"to":[46,98,147],"enforce":[47],"smoothness":[48],"functions,":[51],"in":[52,57],"fact":[53],"makes":[54],"them":[55],"analytic":[56],"strip":[59],"half-width":[61],"$h\u03c0/2$.":[62],"Polynomial":[63],"regression":[64],"then":[65],"estimates":[66],"at":[70],"$\\tilde{O}(1/\\sqrt{n})$,":[72],"with":[73],"explicit":[74],"constants,":[75],"qualitative":[77],"improvement":[78],"over":[79],"$O(n^{-1/4})$":[81],"achievable":[83],"by":[84],"bucketing":[85],"or":[86],"kernel":[87],"smoothing.":[88],"A":[89],"matching":[90],"$\u03a9(1/\\sqrt{n})$":[91],"lower":[92],"bound":[93],"establishes":[94],"optimality":[96],"up":[97],"logarithmic":[99],"factors.":[100],"As":[101],"corollary,":[103],"we":[104,135],"give":[105],"first":[107],"finite-sample":[108],"guarantee":[109],"Platt":[112],"scaling,":[113],"yielding":[114],"post-hoc":[116],"procedure":[117],"recalibrates":[119],"both":[120],"mean":[122],"prediction":[123],"and":[124,143,162],"epistemic-variance":[126],"any":[129],"predictor.":[131],"Along":[132],"way,":[134],"provide":[136],"bucket-free":[138],"definition":[139],"relate":[144],"it":[145],"quantitatively":[146],"bucketed":[149],"formulation":[150],"Ahdritz":[152],"et":[153],"al.":[154],"[2025].":[155],"experiments":[157],"confirm":[158],"predicted":[160],"quality":[164],"recalibrated":[167],"uncertainties.":[168]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-12T00:00:00"}