{"id":"https://openalex.org/W4403662434","doi":"https://doi.org/10.48550/arxiv.2408.03746","title":"Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling","display_name":"Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling","publication_year":2024,"publication_date":"2024-08-07","ids":{"openalex":"https://openalex.org/W4403662434","doi":"https://doi.org/10.48550/arxiv.2408.03746"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2408.03746","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.03746","pdf_url":"https://arxiv.org/pdf/2408.03746","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.03746","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101031423","display_name":"Jian Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Jian","raw_affiliation_strings":["South China University of Technoledge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technoledge","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111321072","display_name":"Zhiqi Lin","orcid":"https://orcid.org/0009-0002-4158-3524","observed_orcids":["https://orcid.org/0009-0002-4158-3524"]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin, Zhiqi","raw_affiliation_strings":["South China University of Technoledge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technoledge","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111252812","display_name":"Shigui Li","orcid":"https://orcid.org/0000-0003-2606-3600","observed_orcids":["https://orcid.org/0000-0003-2606-3600"]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Shigui","raw_affiliation_strings":["South China University of Technoledge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technoledge","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337209","display_name":"Min Chen","orcid":"https://orcid.org/0000-0002-0960-4447","observed_orcids":["https://orcid.org/0000-0002-0960-4447","https://orcid.org/0009-0000-9066-8247","https://orcid.org/0009-0009-2371-5547","https://orcid.org/0000-0002-9478-105X","https://orcid.org/0009-0004-7529-010X"]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Min","raw_affiliation_strings":["South China University of Technoledge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technoledge","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101795525","display_name":"Junmei Yang","orcid":"https://orcid.org/0000-0002-9677-0768","observed_orcids":["https://orcid.org/0000-0002-9677-0768"]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Junmei","raw_affiliation_strings":["South China University of Technoledge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technoledge","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005221942","display_name":"Delu Zeng","orcid":"https://orcid.org/0000-0001-7322-1873","observed_orcids":["https://orcid.org/0000-0001-7322-1873"]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeng, Delu","raw_affiliation_strings":["South China University of Technoledge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technoledge","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110662445","display_name":"John William Paisley","orcid":"https://orcid.org/0009-0009-4890-8230","observed_orcids":["https://orcid.org/0009-0009-4890-8230"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paisley, John","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.8476999998092651,"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":0.8476999998092651,"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":0.13120000064373016,"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":0.0031999999191612005,"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/implicit-priors","display_name":"implicit priors","score":0.9160000085830688},{"id":"https://openalex.org/keywords/diffusion-posterior-sampling","display_name":"diffusion posterior sampling","score":0.847000002861023},{"id":"https://openalex.org/keywords/variational-bayesian-inference","display_name":"variational inference","score":0.6330000162124634},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"uncertainty quantification","score":0.652999997138977},{"id":"https://openalex.org/keywords/non-gaussian-priors","display_name":"non-Gaussian priors","score":0.7519999742507935},{"id":"https://openalex.org/keywords/variational-lower-bound","display_name":"variational lower bound","score":0.6959999799728394},{"id":"https://openalex.org/keywords/out-of-distribution-detection","display_name":"out-of-distribution detection","score":0.9210000038146973},{"id":"https://openalex.org/keywords/calibration","display_name":"calibration","score":0.4359999895095825}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.8746806383132935},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.7132593989372253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5705960988998413},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4991450309753418},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.46480002999305725},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.4526039659976959},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4331366717815399},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3457202613353729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3405230939388275},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3224676549434662},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08672207593917847},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06931012868881226},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2408.03746","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.03746","pdf_url":"https://arxiv.org/pdf/2408.03746","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2408.03746","doi":"https://doi.org/10.48550/arxiv.2408.03746","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.03746","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.03746","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.03746","pdf_url":"https://arxiv.org/pdf/2408.03746","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403662434.pdf","grobid_xml":"https://content.openalex.org/works/W4403662434.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2467604901","https://openalex.org/W2908510526","https://openalex.org/W3110257065","https://openalex.org/W3216280682","https://openalex.org/W4286903878","https://openalex.org/W4322717473","https://openalex.org/W4383180711","https://openalex.org/W4409347738"],"related_works":["https://openalex.org/W4394948139","https://openalex.org/W3158575931","https://openalex.org/W7155031542","https://openalex.org/W4388240333","https://openalex.org/W7127449204","https://openalex.org/W7020974079","https://openalex.org/W3093602668","https://openalex.org/W4396778399","https://openalex.org/W4404573550","https://openalex.org/W2966381196"],"abstract_inverted_index":{"Bayesian":[0,22,35,72,100],"Last":[1,36],"Layer":[2,37],"(BLL)":[3,38],"models":[4,39],"focus":[5],"solely":[6],"on":[7],"uncertainty":[8,151],"in":[9,34,85],"the":[10,25,121,143],"output":[11],"layer":[12,32,74],"of":[13,27,71,124],"neural":[14],"networks,":[15],"demonstrating":[16],"comparable":[17],"performance":[18],"to":[19,119],"more":[20],"complex":[21],"models.":[23],"However,":[24],"use":[26],"Gaussian":[28],"priors":[29,67,84],"for":[30,68,81,91,146],"last":[31,73],"weights":[33],"limits":[40],"their":[41],"expressive":[42,122],"capacity":[43],"when":[44],"faced":[45],"with":[46,88],"non-Gaussian,":[47],"outlier-rich,":[48],"or":[49],"high-dimensional":[50],"datasets.":[51],"To":[52],"address":[53],"this":[54],"shortfall,":[55],"we":[56],"introduce":[57],"a":[58,98],"novel":[59],"approach":[60],"that":[61],"combines":[62],"diffusion":[63,89],"techniques":[64],"and":[65,102,110,131,138,150],"implicit":[66,79],"variational":[69,113],"learning":[70],"weights.":[75],"This":[76],"method":[77,117],"leverages":[78],"distributions":[80],"modeling":[82],"weight":[83],"BLL,":[86],"coupled":[87],"samplers":[90],"approximating":[92],"true":[93],"posterior":[94,103],"predictions,":[95],"thereby":[96],"establishing":[97],"comprehensive":[99],"prior":[101],"estimation":[104],"strategy.":[105],"By":[106],"delivering":[107],"an":[108],"explicit":[109],"computationally":[111],"efficient":[112],"lower":[114],"bound,":[115],"our":[116],"aims":[118],"augment":[120],"abilities":[123],"BLL":[125],"models,":[126],"enhancing":[127],"model":[128],"accuracy,":[129],"calibration,":[130],"out-of-distribution":[132],"detection":[133],"proficiency.":[134],"Through":[135],"detailed":[136],"exploration":[137],"experimental":[139],"validation,":[140],"We":[141],"showcase":[142],"method's":[144],"potential":[145],"improving":[147],"predictive":[148],"accuracy":[149],"quantification":[152],"while":[153],"ensuring":[154],"computational":[155],"efficiency.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-10-23T00:00:00"}