{"id":"https://openalex.org/W7130410562","doi":"https://doi.org/10.48550/arxiv.2602.15136","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","display_name":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7130410562","doi":"https://doi.org/10.48550/arxiv.2602.15136"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.15136","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15136","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.15136","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126299938","display_name":"Nick Cannella","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cannella, Nick","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123907641","display_name":"Anzo Teh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Teh, Anzo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126283688","display_name":"Yanjun Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Yanjun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124023891","display_name":"Yury Polyanskiy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Polyanskiy, Yury","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5126299938"],"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.26660001277923584,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.26660001277923584,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.18490000069141388,"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":0.10249999910593033,"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/prior-probability","display_name":"Prior probability","score":0.7516000270843506},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.6060000061988831},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.578499972820282},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5285000205039978},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5127999782562256},{"id":"https://openalex.org/keywords/bayes-factor","display_name":"Bayes factor","score":0.5019000172615051},{"id":"https://openalex.org/keywords/frequentist-inference","display_name":"Frequentist inference","score":0.46650001406669617},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.4438999891281128},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.4431999921798706},{"id":"https://openalex.org/keywords/bayesian-hierarchical-modeling","display_name":"Bayesian hierarchical modeling","score":0.3919000029563904}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7516000270843506},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.6060000061988831},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.578499972820282},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5285000205039978},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5120000243186951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5101000070571899},{"id":"https://openalex.org/C142291917","wikidata":"https://www.wikidata.org/wiki/Q4165283","display_name":"Bayes factor","level":4,"score":0.5019000172615051},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4797999858856201},{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.46650001406669617},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4431999921798706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4417000114917755},{"id":"https://openalex.org/C191413810","wikidata":"https://www.wikidata.org/wiki/Q17100952","display_name":"Bayesian hierarchical modeling","level":4,"score":0.3919000029563904},{"id":"https://openalex.org/C37903108","wikidata":"https://www.wikidata.org/wiki/Q4874474","display_name":"Bayesian linear regression","level":4,"score":0.3700000047683716},{"id":"https://openalex.org/C101112237","wikidata":"https://www.wikidata.org/wiki/Q4874481","display_name":"Bayesian statistics","level":4,"score":0.36399999260902405},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C80478641","wikidata":"https://www.wikidata.org/wiki/Q195771","display_name":"Sequential analysis","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C99173435","wikidata":"https://www.wikidata.org/wiki/Q4874469","display_name":"Bayesian experimental design","level":5,"score":0.3287999927997589},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C127043819","wikidata":"https://www.wikidata.org/wiki/Q16243608","display_name":"Bayesian programming","level":5,"score":0.3165999948978424},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31520000100135803},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C97933134","wikidata":"https://www.wikidata.org/wiki/Q5374249","display_name":"Empirical probability","level":4,"score":0.30559998750686646},{"id":"https://openalex.org/C99087107","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' rule","level":5,"score":0.2980000078678131},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.2766999900341034},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.2720000147819519},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C68022304","wikidata":"https://www.wikidata.org/wiki/Q842217","display_name":"Bayes estimator","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.15136","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15136","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.15136","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15136","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,28],"theoretically":[1],"justify":[2],"the":[3,39,71,97,108,124,131,136,140],"recent":[4],"empirical":[5,24],"finding":[6],"of":[7,73,87,100,126],"[Teh":[8],"et":[9],"al.,":[10],"2025]":[11],"that":[12,77,107],"a":[13,48,54,83,146],"transformer":[14,110],"pretrained":[15,49,109],"on":[16,23,65],"synthetically":[17],"generated":[18],"data":[19],"achieves":[20],"strong":[21],"performance":[22],"Bayes":[25,50],"(EB)":[26],"problems.":[27],"take":[29],"an":[30],"indirect":[31],"approach":[32],"to":[33,60,112],"this":[34],"question:":[35],"rather":[36],"than":[37],"analyzing":[38],"model":[40,141],"architecture":[41],"or":[42],"training":[43,56,78,137],"dynamics,":[44],"we":[45,69],"ask":[46],"why":[47],"estimator,":[51],"trained":[52],"under":[53,79],"prespecified":[55],"distribution,":[57],"can":[58],"adapt":[59],"arbitrary":[61],"test":[62,92,114,132],"distributions.":[63,93],"Focusing":[64],"Poisson":[66],"EB":[67],"problems,":[68],"identify":[70],"existence":[72],"universal":[74],"priors":[75,81],"such":[76],"these":[80],"yields":[82],"near-optimal":[84],"regret":[85],"bound":[86],"$\\widetilde{O}(\\frac{1}{n})$":[88],"uniformly":[89],"over":[90],"all":[91],"Our":[94],"analysis":[95],"leverages":[96],"classical":[98],"phenomenon":[99,125],"posterior":[101,118],"contraction":[102],"in":[103,129],"Bayesian":[104,143],"statistics,":[105],"showing":[106],"adapts":[111],"unknown":[113],"distributions":[115],"precisely":[116],"through":[117],"contraction.":[119],"This":[120],"perspective":[121],"also":[122],"explains":[123],"length":[127,134],"generalization,":[128],"which":[130],"sequence":[133],"exceeds":[135],"length,":[138],"as":[139],"performs":[142],"inference":[144],"using":[145],"generalized":[147],"posterior.":[148]},"counts_by_year":[],"updated_date":"2026-02-19T06:31:58.851227","created_date":"2026-02-19T00:00:00"}