{"id":"https://openalex.org/W2947972834","doi":null,"title":"Bayesian Prior Networks with PAC Training","display_name":"Bayesian Prior Networks with PAC Training","publication_year":2019,"publication_date":"2019-06-03","ids":{"openalex":"https://openalex.org/W2947972834","mag":"2947972834"},"language":"en","primary_location":{"id":"mag:2947972834","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.00816.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.00816.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027905655","display_name":"Manuel Hau\u00dfmann","orcid":"https://orcid.org/0000-0002-8967-0849","observed_orcids":["https://orcid.org/0000-0002-8967-0849"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manuel Hau\u00dfmann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005295451","display_name":"Sebastian Gerwinn","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian Gerwinn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032539965","display_name":"Melih Kandemir","orcid":"https://orcid.org/0000-0001-6293-3656","observed_orcids":["https://orcid.org/0000-0001-6293-3656"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Melih Kandemir","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6293-3656","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":1,"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":0.9810000061988831,"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":0.9810000061988831,"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":0.010900000110268593,"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/T10320","display_name":"Neural Networks and Applications","score":0.0010999999940395355,"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/bayesian-neural-networks","display_name":"Bayesian neural networks","score":0.9890000224113464},{"id":"https://openalex.org/keywords/empirical-bayes","display_name":"empirical Bayes","score":0.8690000176429749},{"id":"https://openalex.org/keywords/pac-bounds","display_name":"PAC bounds","score":0.902999997138977},{"id":"https://openalex.org/keywords/posterior-predictive-distribution","display_name":"posterior predictive distribution","score":0.5849999785423279},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.7350000143051147},{"id":"https://openalex.org/keywords/forecast-uncertainty","display_name":"forecast uncertainty","score":0.6230000257492065},{"id":"https://openalex.org/keywords/out-of-domain-detection","display_name":"out-of-domain detection","score":0.7829999923706055},{"id":"https://openalex.org/keywords/marginal-likelihood","display_name":"marginal likelihood","score":0.515999972820282},{"id":"https://openalex.org/keywords/complexity-penalty","display_name":"complexity penalty","score":0.5759999752044678},{"id":"https://openalex.org/keywords/uncertainty-estimation","display_name":"uncertainty estimation","score":0.4560000002384186}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8501485586166382},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6445645093917847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6237158179283142},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5510783195495605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5463902354240417},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5292351245880127},{"id":"https://openalex.org/C37903108","wikidata":"https://www.wikidata.org/wiki/Q4874474","display_name":"Bayesian linear regression","level":4,"score":0.5190656781196594},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5154672265052795},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.49896836280822754},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.49105048179626465},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.481427401304245},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.48005211353302},{"id":"https://openalex.org/C99173435","wikidata":"https://www.wikidata.org/wiki/Q4874469","display_name":"Bayesian experimental design","level":5,"score":0.43004217743873596},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2947972834","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.00816.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2947972834","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.00816.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W35527955","https://openalex.org/W582134693","https://openalex.org/W1510659740","https://openalex.org/W1567512734","https://openalex.org/W1628829797","https://openalex.org/W1988520084","https://openalex.org/W2010629420","https://openalex.org/W2029029543","https://openalex.org/W2123045220","https://openalex.org/W2139701068","https://openalex.org/W2149991487","https://openalex.org/W2176412452","https://openalex.org/W2257113116","https://openalex.org/W2547875792","https://openalex.org/W2560321925","https://openalex.org/W2600383743","https://openalex.org/W2785626633","https://openalex.org/W2788755844","https://openalex.org/W2788907134","https://openalex.org/W2804602357","https://openalex.org/W2891630298","https://openalex.org/W2915008147","https://openalex.org/W2950177356","https://openalex.org/W2950471516","https://openalex.org/W2951266961","https://openalex.org/W2951595529","https://openalex.org/W2963509076","https://openalex.org/W3132339071","https://openalex.org/W7094282185"],"related_works":["https://openalex.org/W3119775690","https://openalex.org/W3132339071","https://openalex.org/W2966381196","https://openalex.org/W3197221587","https://openalex.org/W6986697597","https://openalex.org/W4406733370","https://openalex.org/W4323240377","https://openalex.org/W3200935055","https://openalex.org/W4403936288","https://openalex.org/W3160580080"],"abstract_inverted_index":{"We":[0,98,142],"propose":[1],"to":[2,14,94],"train":[3],"Bayesian":[4,46,137],"Neural":[5],"Networks":[6],"(BNNs)":[7],"by":[8,104],"empirical":[9],"Bayes":[10],"as":[11],"an":[12,22,133,157],"alternative":[13],"posterior":[15,54,60],"weight":[16,61],"inference.":[17],"By":[18],"approximately":[19],"marginalizing":[20],"out":[21],"i.i.d.":[23],"realization":[24],"of":[25,29,71,101,115,139],"a":[26,42,67,92,106,119],"finite":[27],"number":[28,70],"sibling":[30],"weights":[31,79],"per":[32],"data-point":[33],"using":[34],"the":[35,53,58,77,86,112,116,127,168],"Central":[36],"Limit":[37],"Theorem":[38],"(CLT),":[39],"we":[40],"attain":[41],"scalable":[43,154],"and":[44,82,118,135,148],"effective":[45,134],"deep":[47],"predictor.":[48],"This":[49],"approach":[50],"directly":[51],"models":[52],"predictive":[55],"distribution,":[56],"by-passing":[57],"intractable":[59],"inference":[62],"step.":[63],"However,":[64],"it":[65],"introduces":[66],"prohibitively":[68],"large":[69],"hyperparameters":[72,83],"for":[73],"stable":[74],"training.":[75],"As":[76],"prior":[78,96,128],"are":[80,84],"marginalized":[81],"optimized,":[85],"model":[87,159],"also":[88],"no":[89],"longer":[90],"provides":[91,156],"means":[93],"incorporate":[95],"knowledge.":[97],"overcome":[99],"both":[100],"these":[102],"drawbacks":[103],"deriving":[105],"trivial":[107],"PAC":[108],"bound":[109],"that":[110,152],"comprises":[111],"marginal":[113],"likelihood":[114],"predictor":[117],"complexity":[120],"penalty.":[121],"The":[122],"outcome":[123],"integrates":[124],"organically":[125],"into":[126],"networks":[129],"framework,":[130],"bringing":[131],"about":[132],"holistic":[136],"treatment":[138],"prediction":[140],"uncertainty.":[141],"observe":[143],"on":[144],"various":[145],"regression,":[146],"classification,":[147],"out-of-domain":[149],"detection":[150],"benchmarks":[151],"our":[153],"method":[155],"improved":[158],"fit":[160],"accompanied":[161],"with":[162],"significantly":[163],"better":[164],"uncertainty":[165],"estimates":[166],"than":[167],"state-of-the-art.":[169]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-06-07T00:00:00"}