{"id":"https://openalex.org/W7131382207","doi":"https://doi.org/10.48550/arxiv.2602.19126","title":"Robust Predictive Uncertainty and Double Descent in Contaminated Bayesian Random Features","display_name":"Robust Predictive Uncertainty and Double Descent in Contaminated Bayesian Random Features","publication_year":2026,"publication_date":"2026-02-22","ids":{"openalex":"https://openalex.org/W7131382207","doi":"https://doi.org/10.48550/arxiv.2602.19126"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.19126","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.19126","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.2602.19126","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126845395","display_name":"Michele Caprio","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Caprio, Michele","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126697320","display_name":"Katerina Papagiannouli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Papagiannouli, Katerina","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051223998","display_name":"Siu Lun Chau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chau, Siu Lun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126114492","display_name":"Sayan Mukherjee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mukherjee, Sayan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5126845395"],"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.44530001282691956,"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":0.44530001282691956,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.11330000311136246,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.09600000083446503,"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":0.6567000150680542},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5045999884605408},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.45899999141693115},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4140999913215637},{"id":"https://openalex.org/keywords/predictive-inference","display_name":"Predictive inference","score":0.4129999876022339},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.40950000286102295},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.38370001316070557},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.3522000014781952}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6801000237464905},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6567000150680542},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5045999884605408},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.45899999141693115},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.4129999876022339},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.40950000286102295},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.38370001316070557},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3828999996185303},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33090001344680786},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.325300008058548},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.32010000944137573},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.3125999867916107},{"id":"https://openalex.org/C37903108","wikidata":"https://www.wikidata.org/wiki/Q4874474","display_name":"Bayesian linear regression","level":4,"score":0.310699999332428},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.19126","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.19126","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.2602.19126","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.19126","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,62,108,136],"propose":[1],"a":[2,92,143,168],"robust":[3,117],"Bayesian":[4,33,60,172],"formulation":[5],"of":[6,95],"random":[7,173],"feature":[8],"(RF)":[9],"regression":[10],"that":[11,123,153],"accounts":[12],"explicitly":[13],"for":[14,68,116,147,161,171],"prior":[15,44,85,195],"and":[16,32,38,45,49,54,65,72,86,121,151,186,196],"likelihood":[17,46,87,197],"misspecification":[18],"via":[19,130],"Huber-style":[20],"contamination":[21,82,94],"sets.":[22],"Starting":[23],"from":[24],"the":[25,42,69,96,104,148,156,181],"classical":[26,105,182],"equivalence":[27],"between":[28],"ridge-regularized":[29],"RF":[30,162],"training":[31],"inference":[34,56],"with":[35,47],"Gaussian":[36,106,133],"priors":[37],"likelihoods,":[39],"we":[40],"replace":[41],"single":[43],"$\u03b5$-":[48],"$\u03b7$-contaminated":[50],"credal":[51],"sets,":[52],"respectively,":[53],"perform":[55],"using":[57],"pessimistic":[58],"generalized":[59],"updating.":[61],"derive":[63],"explicit":[64,190],"tractable":[66],"bounds":[67,78,141],"resulting":[70],"lower":[71],"upper":[73,149],"posterior":[74,97],"predictive":[75,98,118,139,175],"densities.":[76],"These":[77],"show":[79,122],"that,":[80],"when":[81],"is":[83,187],"moderate,":[84],"ambiguity":[88],"effectively":[89],"acts":[90],"as":[91],"direct":[93],"distribution,":[99],"yielding":[100],"uncertainty":[101,119,176],"envelopes":[102],"around":[103],"predictive.":[107],"introduce":[109],"an":[110,126,131],"Imprecise":[111],"Highest":[112],"Density":[113],"Region":[114],"(IHDR)":[115],"quantification":[120],"it":[124],"admits":[125],"efficient":[127],"outer":[128],"approximation":[129,146],"adjusted":[132],"credible":[134],"interval.":[135],"further":[137],"obtain":[138],"variance":[140],"(under":[142],"mild":[144],"truncation":[145],"bound)":[150],"prove":[152],"they":[154],"preserve":[155],"leading-order":[157],"proportional-growth":[158],"asymptotics":[159],"known":[160],"models.":[163],"Together,":[164],"these":[165],"results":[166],"establish":[167],"robustness":[169],"theory":[170],"features:":[174],"remains":[177],"computationally":[178],"tractable,":[179],"inherits":[180],"double-descent":[183],"phase":[184],"structure,":[185],"improved":[188],"by":[189],"worst-case":[191],"guarantees":[192],"under":[193],"bounded":[194],"misspecification.":[198]},"counts_by_year":[],"updated_date":"2026-02-26T06:34:08.959763","created_date":"2026-02-26T00:00:00"}