{"id":"https://openalex.org/W7155058434","doi":"https://doi.org/10.48550/arxiv.2604.17219","title":"PAC-Bayes Bounds for Gibbs Posteriors via Singular Learning Theory","display_name":"PAC-Bayes Bounds for Gibbs Posteriors via Singular Learning Theory","publication_year":2026,"publication_date":"2026-04-19","ids":{"openalex":"https://openalex.org/W7155058434","doi":"https://doi.org/10.48550/arxiv.2604.17219"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.17219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17219","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.17219","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134195035","display_name":"Chenyang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chenyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134189368","display_name":"Yun Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yun","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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.45899999141693115,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.45899999141693115,"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/T12303","display_name":"Tensor decomposition and applications","score":0.2037999927997589,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.15970000624656677,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6503999829292297},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4408000111579895},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4041000008583069},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3912999927997589},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.3763999938964844},{"id":"https://openalex.org/keywords/statistical-learning-theory","display_name":"Statistical learning theory","score":0.37130001187324524},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.362199991941452},{"id":"https://openalex.org/keywords/matrix-norm","display_name":"Matrix norm","score":0.3483000099658966}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6503999829292297},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6384000182151794},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5507000088691711},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4408000111579895},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C2779915298","wikidata":"https://www.wikidata.org/wiki/Q7604400","display_name":"Statistical learning theory","level":3,"score":0.37130001187324524},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C92207270","wikidata":"https://www.wikidata.org/wiki/Q939253","display_name":"Matrix norm","level":3,"score":0.3483000099658966},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.2840999960899353},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2822999954223633},{"id":"https://openalex.org/C145242015","wikidata":"https://www.wikidata.org/wiki/Q774123","display_name":"Approximation theory","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C2777634741","wikidata":"https://www.wikidata.org/wiki/Q768993","display_name":"Wasserstein metric","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C29406490","wikidata":"https://www.wikidata.org/wiki/Q1420659","display_name":"Fisher information","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C109282560","wikidata":"https://www.wikidata.org/wiki/Q4166054","display_name":"Singular value","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C16171025","wikidata":"https://www.wikidata.org/wiki/Q863349","display_name":"Singularity","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C73586568","wikidata":"https://www.wikidata.org/wiki/Q2600211","display_name":"Parameter space","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.17219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17219","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.17219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17219","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,"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"},"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],"derive":[1],"explicit":[2,41,98],"non-asymptotic":[3],"PAC-Bayes":[4,140],"generalization":[5,145],"bounds":[6,31,58,123],"for":[7,142],"Gibbs":[8],"posteriors,":[9],"that":[10,59,120],"is,":[11],"data-dependent":[12],"distributions":[13],"over":[14,83],"model":[15,45,75],"parameters":[16],"obtained":[17],"by":[18],"exponentially":[19],"tilting":[20],"a":[21,80],"prior":[22],"with":[23],"the":[24,44,69,73,84,104,121,137],"empirical":[25],"risk.":[26,106],"Unlike":[27],"classical":[28,131],"worst-case":[29],"complexity":[30],"based":[32],"on":[33],"uniform":[34],"laws":[35],"of":[36,43,49,103,139],"large":[37],"numbers,":[38],"which":[39,87],"require":[40],"control":[42],"space":[46],"in":[47,147],"terms":[48],"metric":[50],"entropy":[51],"(integrals),":[52],"our":[53],"analysis":[54,141],"yields":[55],"posterior-averaged":[56],"risk":[57],"can":[60],"be":[61],"applied":[62],"to":[63,68,96,108],"overparameterized":[64,149],"models":[65],"and":[66,72,99,112,117,127,150],"adapt":[67],"data":[70],"structure":[71],"intrinsic":[74],"complexity.":[76],"The":[77],"bound":[78],"involves":[79],"marginal-type":[81],"integral":[82],"parameter":[85],"space,":[86],"we":[88],"analyze":[89],"using":[90],"tools":[91],"from":[92],"singular":[93,151],"learning":[94],"theory":[95],"obtain":[97],"practically":[100],"meaningful":[101],"characterizations":[102],"posterior":[105],"Applications":[107],"low-rank":[109],"matrix":[110],"completion":[111],"ReLU":[113],"neural":[114],"network":[115],"regression":[116],"classification":[118],"show":[119],"resulting":[122],"are":[124],"analytically":[125],"tractable":[126],"substantially":[128],"tighter":[129],"than":[130],"complexity-based":[132],"bounds.":[133],"Our":[134],"results":[135],"highlight":[136],"potential":[138],"precise":[143],"finite-sample":[144],"guarantees":[146],"modern":[148],"models.":[152]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-22T00:00:00"}