{"id":"https://openalex.org/W7164903684","doi":"https://doi.org/10.48550/arxiv.2606.16214","title":"Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learning","display_name":"Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learning","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164903684","doi":"https://doi.org/10.48550/arxiv.2606.16214"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.16214","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.16214","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.16214","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113306668","display_name":"T. Wieczorek","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wieczorek, Tobias Jan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064188372","display_name":"Le\u00f3n Andrade","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"de Andrade, Leon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008471432","display_name":"Thomas M\u00f6llenhoff","orcid":"https://orcid.org/0000-0001-7730-0843"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M\u00f6llenhoff, Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138733035","display_name":"Marcus Rohrbach","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohrbach, Marcus","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.2976999878883362,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.2976999878883362,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.2402999997138977,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09889999777078629,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6234999895095825},{"id":"https://openalex.org/keywords/propagation-of-uncertainty","display_name":"Propagation of uncertainty","score":0.5748999714851379},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5746999979019165},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.44029998779296875},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4366999864578247},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.4325999915599823},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4171000123023987},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.37290000915527344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6348999738693237},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6234999895095825},{"id":"https://openalex.org/C123614077","wikidata":"https://www.wikidata.org/wiki/Q1364905","display_name":"Propagation of uncertainty","level":2,"score":0.5748999714851379},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5746999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5019000172615051},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4341999888420105},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3783999979496002},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.35989999771118164},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.33329999446868896},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32170000672340393},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3190999925136566},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.31060001254081726},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2727999985218048}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.16214","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.16214","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.16214","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.16214","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":"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":{"Modern":[0],"deep":[1],"learning":[2,22],"models":[3],"remain":[4],"notoriously":[5],"prone":[6],"to":[7,18,41,94,100,151,177,188,197],"overconfidence,":[8],"limiting":[9],"their":[10,92],"reliability":[11],"in":[12,80],"high-stakes":[13],"applications.":[14],"Bayesian":[15],"methods":[16],"aim":[17],"counter":[19],"this":[20,33,110],"by":[21],"a":[23,44,81,120,141,159],"distribution":[24],"over":[25],"model":[26],"parameters,":[27],"and":[28,103,136,156,185],"recent":[29,130],"advances":[30],"now":[31],"make":[32],"feasible":[34],"for":[35,90,124,132],"large-scale":[36],"architectures":[37,96],"at":[38,47,158,172],"costs":[39],"comparable":[40],"AdamW.":[42],"However,":[43],"challenge":[45],"remains":[46,97],"test":[48],"time:":[49],"predictions":[50],"must":[51],"be":[52],"averaged":[53],"across":[54,154],"many":[55],"forward":[56,83],"passes":[57],"with":[58,129,179,190,194],"weights":[59],"sampled":[60],"from":[61,175,186],"the":[62,162],"posterior,":[63],"which":[64,118],"is":[65],"prohibitively":[66],"expensive.":[67],"Variance":[68,115],"propagation":[69,122,167],"offers":[70],"an":[71],"efficient":[72],"alternative,":[73],"computing":[74],"layer-wise":[75],"analytical":[76],"approximations":[77],"of":[78,105,161],"uncertainty":[79,149],"single":[82],"pass.":[84],"While":[85],"such":[86],"techniques":[87,131],"are":[88],"effective":[89],"MLPs,":[91],"extension":[93],"modern":[95],"challenging,":[98],"due":[99],"increased":[101],"depth":[102],"diversity":[104],"layer":[106],"types.":[107],"To":[108],"fill":[109],"gap,":[111],"we":[112],"propose":[113],"Calibrated":[114],"Propagation":[116],"(CVP),":[117],"introduces":[119],"new":[121],"method":[123],"normalization":[125],"layers,":[126],"combines":[127],"it":[128],"handling":[133],"activation":[134],"functions,":[135],"absorbs":[137],"residual":[138],"error":[139],"through":[140],"light":[142],"calibration":[143],"step.":[144],"CVP":[145,169],"yields":[146],"comparably":[147],"accurate":[148],"estimates":[150],"MC":[152],"sampling":[153],"transformers":[155],"CNNs,":[157],"fraction":[160],"cost.":[163],"Against":[164],"prior":[165],"variance":[166],"work,":[168],"improves":[170],"coverage":[171],"$0.5\\%$":[173],"risk":[174],"$8.2\\%$":[176],"$14.6\\%$":[178],"BEiT-3":[180],"on":[181,192],"Visual":[182],"Reasoning":[183],"(NLVR2)":[184],"$2.6\\%$":[187],"$10.8\\%$":[189],"ViLT":[191],"VQAv2,":[193],"gains":[195],"extending":[196],"convolutional":[198],"architectures.":[199]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-17T00:00:00"}