{"id":"https://openalex.org/W7214405574","doi":"https://doi.org/10.48550/arxiv.2609.29622","title":"Optimal Recovery Meets Bayesian Learning: Where Worst-Case Bounds Pay Off","display_name":"Optimal Recovery Meets Bayesian Learning: Where Worst-Case Bounds Pay Off","publication_year":2026,"publication_date":"2026-08-29","ids":{"openalex":"https://openalex.org/W7214405574","doi":"https://doi.org/10.48550/arxiv.2609.29622"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.29622","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29622","pdf_url":"https://arxiv.org/pdf/2609.29622","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/2609.29622","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147393380","display_name":"Gordei Verbii","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Verbii, Gordei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5147393380"],"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.888700008392334,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.888700008392334,"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":0.019200000911951065,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.005900000222027302,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/optimal-recovery","display_name":"optimal recovery","score":0.9169999957084656},{"id":"https://openalex.org/keywords/bayesian-learning","display_name":"Bayesian learning","score":0.8970000147819519},{"id":"https://openalex.org/keywords/gaussian-processes","display_name":"Gaussian processes","score":0.5609999895095825},{"id":"https://openalex.org/keywords/posterior-variance","display_name":"posterior variance","score":0.7519999742507935},{"id":"https://openalex.org/keywords/conformal-prediction","display_name":"conformal prediction","score":0.671999990940094},{"id":"https://openalex.org/keywords/covariate-shift","display_name":"covariate shift","score":0.8270000219345093},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.9139999747276306},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.5109999775886536}],"concepts":[{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6589000225067139},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5182999968528748},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4546000063419342},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.43689998984336853},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43639999628067017},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4320000112056732},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4244000017642975},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.4189000129699707},{"id":"https://openalex.org/C200941418","wikidata":"https://www.wikidata.org/wiki/Q273508","display_name":"Inflation (cosmology)","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C2779652578","wikidata":"https://www.wikidata.org/wiki/Q5442977","display_name":"Fence (mathematics)","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.3330000042915344},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.31769999861717224},{"id":"https://openalex.org/C101112237","wikidata":"https://www.wikidata.org/wiki/Q4874481","display_name":"Bayesian statistics","level":4,"score":0.3140999972820282},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.30489999055862427},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C178635117","wikidata":"https://www.wikidata.org/wiki/Q747499","display_name":"RADIUS","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C99414536","wikidata":"https://www.wikidata.org/wiki/Q7098950","display_name":"Optimal stopping","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.29622","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29622","pdf_url":"https://arxiv.org/pdf/2609.29622","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.2609.29622","doi":"https://doi.org/10.48550/arxiv.2609.29622","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.29622","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:2609.29622","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29622","pdf_url":"https://arxiv.org/pdf/2609.29622","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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214405574.pdf","grobid_xml":"https://content.openalex.org/works/W7214405574.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2880842812","https://openalex.org/W4403598740","https://openalex.org/W7141011836"],"related_works":["https://openalex.org/W7075684732","https://openalex.org/W2593103901","https://openalex.org/W7069948914","https://openalex.org/W3005822368","https://openalex.org/W2903387436","https://openalex.org/W7098561580","https://openalex.org/W2977858920","https://openalex.org/W7026979391","https://openalex.org/W7221808237","https://openalex.org/W6977643373"],"abstract_inverted_index":{"Worst-case":[0],"Optimal":[1],"Recovery":[2],"(OR)":[3],"and":[4,30,43,87,108,143,161,213,223,242,254,278],"Bayesian":[5,48,193],"learning":[6],"describe":[7],"the":[8,17,20,34,51,59,65,89,104,114,127,147,195,225,228,234,251,271,275,280],"same":[9],"Gaussian-quadratic-Hilbert":[10],"problems":[11],"in":[12,224,233],"two":[13],"vocabularies.":[14],"We":[15],"sharpen":[16],"correspondence":[18],"-":[19,42],"radius":[21],"of":[22,98,227],"information":[23],"equals":[24],"a":[25,38,70,96,133,163,178,182,199,209,260,264],"nugget-optimized":[26],"GP":[27],"posterior":[28,35],"variance":[29],"is":[31,57,79,88,172,190,198,219,237,241,259],"attained":[32],"by":[33],"mean":[36],"at":[37,113,215],"closed-form":[39],"balance":[40],"nugget":[41],"measure,":[44],"inside":[45],"three":[46],"published":[47],"systems,":[49],"where":[50,75],"worst-case":[52],"side":[53],"pays.":[54],"The":[55,267],"ledger":[56],"two-sided:":[58],"losses":[60],"instruct":[61],"as":[62,64,230,232],"much":[63,231],"wins.":[66],"Morozov":[67],"calibration":[68],"tracks":[69],"test-access":[71],"oracle":[72,140],"within":[73],"$1.00$-$1.19\\times$":[74],"$\u03c3$-blind":[76],"rules":[77],"fail,":[78],"$4.9$-$6.3\\times$":[80],"more":[81,244],"reproducible":[82],"across":[83],"noise":[84,141],"draws":[85],"($p=0.002$-$0.004$),":[86],"only":[90],"deployable":[91],"rule":[92],"whose":[93,202],"selection":[94],"survives":[95],"change":[97],"backend":[99],"($1.36\\times$":[100],"against":[101],"$12$-$30\\times$":[102],"for":[103],"released":[105],"weight,":[106],"ML-II":[107],"GCV);":[109],"tight":[110],"certificates":[111],"cover":[112],"information-theoretic":[115],"floor":[116,201],"with":[117],"no":[118],"numerical":[119],"slack.":[120],"But":[121],"on":[122,130,152,167,177,243],"exchangeable":[123],"data":[124,276],"split-conformal":[125],"beats":[126],"OR":[128,148],"head":[129],"interval":[131,157],"score,":[132],"water-filling":[134],"prior":[135],"adds":[136],"nothing":[137],"without":[138],"an":[139],"hint,":[142],"under":[144,208],"covariate":[145],"shift":[146,174,176],"band":[149],"keeps":[150],"coverage":[151],"every":[153,216,255],"dataset":[154],"yet":[155],"loses":[156],"score":[158],"to":[159,162,274],"split-conformal,":[160],"feature-free":[164],"constant":[165],"band,":[166],"most":[168],"cells;":[169],"what":[170],"pays":[171],"not":[173,221,263],"but":[175],"learnable":[179],"target,":[180],"which":[181],"training-free":[183],"audit":[184,279],"statistic":[185],"predicts":[186],"before":[187],"any":[188],"model":[189],"fitted.":[191],"In":[192],"optimization":[194],"certified":[196],"width":[197],"validity":[200],"scalar":[203],"inflation":[204,229],"we":[205],"prove":[206],"inert":[207,238],"checkable":[210],"margin":[211],"condition":[212],"check":[214],"step.":[217],"Inertness":[218],"graded,":[220],"binary,":[222],"size":[226],"objective:":[235],"$\u03ba{=}2$":[236],"wherever":[239],"$\u03ba{=}5$":[240,248],"cells":[245],"besides,":[246],"while":[247],"moves":[249],"half":[250],"Ackley":[252],"seeds":[253],"Griewank":[256],"seed.":[257],"Exploration":[258],"shape":[261],"problem,":[262],"scale":[265],"one.":[266],"design":[268],"rule:":[269],"match":[270],"guarantee":[272],"tool":[273],"regime,":[277],"regime":[281],"first.":[282]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-26T00:00:00"}