{"id":"https://openalex.org/W7202289046","doi":"https://doi.org/10.4171/msl/59","title":"Rapid Bayesian computation and estimation for neural networks via log-concave coupling","display_name":"Rapid Bayesian computation and estimation for neural networks via log-concave coupling","publication_year":2026,"publication_date":"2026-08-12","ids":{"openalex":"https://openalex.org/W7202289046","doi":"https://doi.org/10.4171/msl/59"},"language":"en","primary_location":{"id":"doi:10.4171/msl/59","doi":"https://doi.org/10.4171/msl/59","is_oa":true,"landing_page_url":"https://doi.org/10.4171/msl/59","pdf_url":null,"source":{"id":"https://openalex.org/S4210183802","display_name":"Mathematical Statistics and Learning","issn_l":"2520-2316","issn":["2520-2316","2520-2324"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","oarl"],"host_organization":"https://openalex.org/I4389425263","host_organization_name":"EMS Press","host_organization_lineage":["https://openalex.org/I4389425263"],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematical Statistics and Learning","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.4171/msl/59","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061406056","display_name":"Curtis McDonald","orcid":"https://orcid.org/0000-0001-6298-2861","observed_orcids":["https://orcid.org/0000-0001-6298-2861"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Curtis McDonald","raw_affiliation_strings":["University of California, Berkeley, USA"],"raw_orcid":"https://orcid.org/0000-0001-6298-2861","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101799639","display_name":"Andrew R. Barron","orcid":"https://orcid.org/0000-0002-8072-7351","observed_orcids":["https://orcid.org/0000-0002-8072-7351"]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew R. Barron","raw_affiliation_strings":["Yale University, New Haven, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University, New Haven, USA","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"9","issue":"3","first_page":"199","last_page":"246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9984999895095825,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.0005000000237487257,"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":0.0003000000142492354,"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":0.8669999837875366},{"id":"https://openalex.org/keywords/single-hidden-layer-feedforward-neural-network","display_name":"single hidden layer neural network","score":0.9800000190734863},{"id":"https://openalex.org/keywords/markov-chain-mixing","display_name":"Markov chain mixing","score":0.722000002861023},{"id":"https://openalex.org/keywords/l1-regularization","display_name":"L1 regularization","score":0.5899999737739563},{"id":"https://openalex.org/keywords/auxiliary-random-variables","display_name":"auxiliary random variables","score":0.6600000262260437},{"id":"https://openalex.org/keywords/high-dimensional-estimation","display_name":"high-dimensional estimation","score":0.5009999871253967}],"concepts":[{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.754800021648407},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.6179999709129333},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.5825999975204468},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5228999853134155},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4959000051021576},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48899999260902405},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.46950000524520874},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.42179998755455017},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4032999873161316},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.3849000036716461},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.38100001215934753},{"id":"https://openalex.org/C56672385","wikidata":"https://www.wikidata.org/wiki/Q17157111","display_name":"Mixture distribution","level":3,"score":0.38040000200271606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3662000000476837},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.32330000400543213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31790000200271606},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C68022304","wikidata":"https://www.wikidata.org/wiki/Q842217","display_name":"Bayes estimator","level":3,"score":0.3019999861717224},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C170593435","wikidata":"https://www.wikidata.org/wiki/Q4128565","display_name":"Slice sampling","level":4,"score":0.2849000096321106},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C86426650","wikidata":"https://www.wikidata.org/wiki/Q7452504","display_name":"Sequential estimation","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.4171/msl/59","doi":"https://doi.org/10.4171/msl/59","is_oa":true,"landing_page_url":"https://doi.org/10.4171/msl/59","pdf_url":null,"source":{"id":"https://openalex.org/S4210183802","display_name":"Mathematical Statistics and Learning","issn_l":"2520-2316","issn":["2520-2316","2520-2324"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","oarl"],"host_organization":"https://openalex.org/I4389425263","host_organization_name":"EMS Press","host_organization_lineage":["https://openalex.org/I4389425263"],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematical Statistics and Learning","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2411.17667","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2411.17667","pdf_url":"https://arxiv.org/pdf/2411.17667","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.2411.17667","doi":"https://doi.org/10.48550/arxiv.2411.17667","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.17667","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":"doi:10.4171/msl/59","doi":"https://doi.org/10.4171/msl/59","is_oa":true,"landing_page_url":"https://doi.org/10.4171/msl/59","pdf_url":null,"source":{"id":"https://openalex.org/S4210183802","display_name":"Mathematical Statistics and Learning","issn_l":"2520-2316","issn":["2520-2316","2520-2324"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","oarl"],"host_organization":"https://openalex.org/I4389425263","host_organization_name":"EMS Press","host_organization_lineage":["https://openalex.org/I4389425263"],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematical Statistics and Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202289046.pdf","grobid_xml":"https://content.openalex.org/works/W7202289046.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2889756710","https://openalex.org/W2912117543","https://openalex.org/W4399115850","https://openalex.org/W4399115949","https://openalex.org/W4411320045","https://openalex.org/W4412805109"],"related_works":["https://openalex.org/W4401699128","https://openalex.org/W7100685260","https://openalex.org/W3208952487","https://openalex.org/W2981230321","https://openalex.org/W2123256163","https://openalex.org/W264474835","https://openalex.org/W7100553100","https://openalex.org/W3014965073","https://openalex.org/W7097990524","https://openalex.org/W2794065264"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,22,25,46,60,83,87,112,118,135,142,158,162,176,187],"study":[4,21],"of":[5,24,55,80,102,145,161,189],"a":[6,30,74,107,125,197],"Bayesian":[7],"estimation":[8],"procedure":[9],"for":[10,86],"single-hidden-layer":[11],"neural":[12,47],"networks":[13],"using":[14],"\\ell_{1}":[15,113],"controlled":[16],"neuron":[17,170],"weight":[18],"vectors.":[19],"We":[20],"structure":[23],"posterior":[26,84,91,119,177],"density":[27,85,120,127],"and":[28,58,95],"provide":[29],"representation":[31],"that":[32,117,152],"makes":[33],"it":[34],"amenable":[35],"to":[36,99,186],"rapid":[37,100],"sampling":[38,180],"via":[39],"Markov":[40],"Chain":[41],"Monte":[42],"Carlo":[43],"(MCMC).":[44],"Let":[45],"network":[48],"have":[49],"K":[50],"neurons":[51],"with":[52,128,191],"internal":[53,88],"weights":[54,190],"dimension":[56],"d":[57],"fix":[59],"outer":[61],"weights.":[62,89],"Thus,":[63,169],"there":[64],"are":[65,138],"Kd":[66,148,153],"parameters":[67,147,171],"overall.":[68],"With":[69],"N":[70],"data":[71],"observations,":[72],"use":[73],"gain":[75],"parameter":[76],"or":[77],"inverse":[78],"temperature":[79],"\\beta":[81],"in":[82],"The":[90,183],"is":[92,149,166],"intrinsically":[93],"multi-modal":[94],"not":[96],"naturally":[97],"suited":[98],"mixing":[101,159],"direct":[103],"MCMC":[104],"algorithms.":[105],"For":[106],"continuous":[108],"uniform":[109],"prior":[110],"on":[111],"ball,":[114],"we":[115],"demonstrate":[116],"can":[121,172],"be":[122,173],"written":[123],"as":[124,196],"mixture":[126,136],"suitably":[129],"defined":[130],"auxiliary":[131,163,193],"random":[132,164,194],"variables,":[133],"where":[134],"components":[137],"log-concave.":[139,168],"Furthermore,":[140],"when":[141],"total":[143],"number":[144],"model":[146],"large":[150],"enough":[151],"\\geq":[154],"C(\\beta":[155],"N)^{2}":[156],",":[157],"distribution":[160],"variables":[165,195],"also":[167],"sampled":[174],"from":[175],"by":[178],"only":[179],"log-concave":[181,198],"densities.":[182],"authors":[184],"refer":[185],"pairing":[188],"such":[192],"coupling.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-13T00:00:00"}