{"id":"https://openalex.org/W2941968773","doi":"https://doi.org/10.48550/arxiv.1903.02334","title":"Neural Empirical Bayes","display_name":"Neural Empirical Bayes","alternate_titles":[],"publication_year":2019,"publication_date":"2019-03-06","ids":{"openalex":"https://openalex.org/W2941968773","doi":"https://doi.org/10.48550/arxiv.1903.02334","mag":"2941968773"},"language":"en","primary_location":{"id":"pmh:oai:helda.helsinki.fi:10138/309773","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/309773","pdf_url":"http://www.jmlr.org/papers/volume20/19-216/19-216.pdf","source":{"id":"https://openalex.org/S4406922691","display_name":"Helda - University of Helsinki Institutional Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Article"},"parent_works":[],"lineage":["https://openalex.org/W2941968773"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://www.jmlr.org/papers/volume20/19-216/19-216.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005413766","display_name":"Saeed Saremi","orcid":null,"observed_orcids":[]},"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,"contributor_roles":[],"raw_author_name":"Saremi, Saeed","raw_affiliation_strings":["Redwood Center for Theoretical Neuroscience University of California Berkeley , CA 94720-3198 , USA","University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Redwood Center for Theoretical Neuroscience University of California Berkeley , CA 94720-3198 , USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061498233","display_name":"Aapo Hyv\u00e4rinen","orcid":"https://orcid.org/0000-0002-5806-4432","observed_orcids":["https://orcid.org/0000-0002-5806-4432"]},"institutions":[{"id":"https://openalex.org/I32943570","display_name":"Helsinki Institute for Information Technology","ror":"https://ror.org/05kph4940","country_code":"FI","type":"facility","lineage":["https://openalex.org/I133731052","https://openalex.org/I32943570","https://openalex.org/I9927081"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["FI","GB"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Hyvarinen, Aapo","raw_affiliation_strings":["NNAISENSE Inc. , Austin , TX","University College London , UK","Helsingin tietotekniikan tutkimuslaitos"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NNAISENSE Inc. , Austin , TX","institution_ids":[]},{"raw_affiliation_string":"University College London , UK","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"Helsingin tietotekniikan tutkimuslaitos","institution_ids":["https://openalex.org/I32943570"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":82,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":null,"first_page":"1","last_page":"23"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.41110000014305115,"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":0.41110000014305115,"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":0.33719998598098755,"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":0.06350000202655792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/kernel-density-estimation","display_name":"kernel density estimation","score":0.9890000224113464},{"id":"https://openalex.org/keywords/empirical-bayes","display_name":"empirical Bayes","score":0.8080000281333923},{"id":"https://openalex.org/keywords/concentration-of-measure","display_name":"concentration of measure","score":0.9179999828338623},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.8899999856948853},{"id":"https://openalex.org/keywords/energy-function","display_name":"energy function","score":0.5720000267028809},{"id":"https://openalex.org/keywords/associative-memory","display_name":"associative memory","score":0.8920000195503235},{"id":"https://openalex.org/keywords/hopfield-neural-network","display_name":"Hopfield neural network","score":0.8069999814033508},{"id":"https://openalex.org/keywords/gradient-flow","display_name":"gradient flow","score":0.7089999914169312},{"id":"https://openalex.org/keywords/attractors","display_name":"attractors","score":0.9039999842643738},{"id":"https://openalex.org/keywords/high-dimensional-spheres","display_name":"high-dimensional spheres","score":0.7059999704360962},{"id":"https://openalex.org/keywords/creative-memory","display_name":"creative memory","score":0.3179999887943268}],"concepts":[{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.47314512729644775},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.4230368733406067},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.39969104528427124},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39556801319122314},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38150084018707275},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3348793387413025},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.3211624026298523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31898897886276245},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.30096182227134705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.28834202885627747},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.16840746998786926},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:helda.helsinki.fi:10138/309773","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/309773","pdf_url":"http://www.jmlr.org/papers/volume20/19-216/19-216.pdf","source":{"id":"https://openalex.org/S4406922691","display_name":"Helda - University of Helsinki Institutional Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:arXiv.org:1903.02334","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.02334","pdf_url":"https://arxiv.org/pdf/1903.02334","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":"mag:2941968773","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1903.02334","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},{"id":"pmh:oai:HAL:hal-02419496v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02419496","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research, 2019, 20, pp.1 - 23","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.1903.02334","doi":"https://doi.org/10.48550/arxiv.1903.02334","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.02334","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:helda.helsinki.fi:10138/309773","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/309773","pdf_url":"http://www.jmlr.org/papers/volume20/19-216/19-216.pdf","source":{"id":"https://openalex.org/S4406922691","display_name":"Helda - University of Helsinki Institutional Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8850892312","display_name":"RI: Small: Extracting and Understanding Sparse Structure in Spatiotemporal Data in Neuroscience and Other Applications","funder_award_id":"1718991","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2941968773.pdf","grobid_xml":"https://content.openalex.org/works/W2941968773.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W114565888","https://openalex.org/W348507692","https://openalex.org/W602904462","https://openalex.org/W1505878979","https://openalex.org/W1508638168","https://openalex.org/W1511733513","https://openalex.org/W1522301498","https://openalex.org/W1547224907","https://openalex.org/W1573820523","https://openalex.org/W1590636096","https://openalex.org/W1994616650","https://openalex.org/W1995341919","https://openalex.org/W2013035813","https://openalex.org/W2018259456","https://openalex.org/W2022686119","https://openalex.org/W2054640142","https://openalex.org/W2067191022","https://openalex.org/W2072128103","https://openalex.org/W2089674328","https://openalex.org/W2112796928","https://openalex.org/W2118020555","https://openalex.org/W2120340025","https://openalex.org/W2128084896","https://openalex.org/W2136277000","https://openalex.org/W2156909104","https://openalex.org/W2159528849","https://openalex.org/W2163922914","https://openalex.org/W2164500538","https://openalex.org/W2169759423","https://openalex.org/W2212271491","https://openalex.org/W2412287113","https://openalex.org/W2462831000","https://openalex.org/W2604847669","https://openalex.org/W2607038622","https://openalex.org/W2614634292","https://openalex.org/W2765833400","https://openalex.org/W2767286248","https://openalex.org/W2788800397","https://openalex.org/W2804821933","https://openalex.org/W2899771611","https://openalex.org/W2962727772","https://openalex.org/W2962834855","https://openalex.org/W2964121744","https://openalex.org/W2981583734","https://openalex.org/W2982692570","https://openalex.org/W3007103623","https://openalex.org/W3140968660","https://openalex.org/W3157752112","https://openalex.org/W3207342693","https://openalex.org/W4231109964","https://openalex.org/W4249214388","https://openalex.org/W4250954493","https://openalex.org/W4285719527","https://openalex.org/W4293052541","https://openalex.org/W7034449035"],"related_works":["https://openalex.org/W2053179591","https://openalex.org/W3106098916","https://openalex.org/W192573243","https://openalex.org/W2159388368","https://openalex.org/W2114858870","https://openalex.org/W7215107542","https://openalex.org/W2807156663","https://openalex.org/W2909685253","https://openalex.org/W2982649420"],"abstract_inverted_index":{"We":[0,137,187],"unify":[1],"$\\textit{kernel":[2],"density":[3,32,115],"estimation}$":[4],"and":[5,8,50,156,160],"$\\textit{empirical":[6],"Bayes}$":[7],"address":[9],"a":[10,18,59,98,147,162,183],"set":[11,184],"of":[12,21,28,86,116,125,134,178,185,195,202],"problems":[13],"in":[14,25,58],"unsupervised":[15],"learning":[16,70],"with":[17,97],"geometric":[19],"interpretation":[20],"those":[22],"methods,":[23],"rooted":[24],"the":[26,40,54,88,114,132,175,179,189,193],"$\\textit{concentration":[27],"measure}$":[29],"phenomenon.":[30],"Kernel":[31],"is":[33,44,53,72,113,121],"viewed":[34],"symbolically":[35,78],"as":[36,65,123,200],"$X\\rightharpoonup":[37],"Y$":[38],"where":[39,111],"random":[41],"variable":[42],"$X$":[43],"smoothed":[45],"to":[46,56,131,182],"$Y=":[47],"X+N(0,\u03c3^2":[48],"I_d)$,":[49],"empirical":[51,157],"Bayes":[52,158],"machinery":[55],"denoise":[57],"least-squares":[60],"sense,":[61],"which":[62,128],"we":[63,92],"express":[64],"$X":[66,81],"\\leftharpoondown":[67],"Y$.":[68,83],"A":[69],"objective":[71],"derived":[73],"by":[74,80,102,174,191],"combining":[75],"these":[76],"two,":[77],"captured":[79],"\\rightleftharpoons":[82],"Crucially,":[84],"instead":[85],"using":[87],"original":[89],"nonparametric":[90],"estimators,":[91],"parametrize":[93],"$\\textit{the":[94],"energy":[95,181],"function}$":[96],"neural":[99],"network":[100],"denoted":[101],"$\u03d5$;":[103],"at":[104],"optimality,":[105],"$\\nabla":[106],"\u03d5\\approx":[107],"-\\nabla":[108],"\\log":[109],"f$":[110],"$f$":[112],"$Y$.":[117],"The":[118],"optimization":[119],"problem":[120],"abstracted":[122],"interactions":[124],"high-dimensional":[126],"spheres":[127],"emerge":[129],"due":[130],"concentration":[133],"isotropic":[135],"gaussians.":[136],"introduce":[138],"two":[139],"algorithmic":[140],"frameworks":[141],"based":[142],"on":[143],"this":[144],"machinery:":[145],"(i)":[146],"\"walk-jump\"":[148],"sampling":[149],"scheme":[150],"that":[151],"combines":[152],"Langevin":[153],"MCMC":[154],"(walks)":[155],"(jumps),":[159],"(ii)":[161],"probabilistic":[163],"framework":[164],"for":[165,204],"$\\textit{associative":[166],"memory}$,":[167],"called":[168],"NEBULA,":[169],"defined":[170],"\u00e0":[171],"la":[172],"Hopfield":[173],"$\\textit{gradient":[176],"flow}$":[177],"learned":[180],"attractors.":[186],"finish":[188],"paper":[190],"reporting":[192],"emergence":[194],"very":[196],"rich":[197],"\"creative":[198],"memories\"":[199],"attractors":[201],"NEBULA":[203],"highly-overlapping":[205],"spheres.":[206]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2941968773","counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":3}],"updated_date":"2026-11-20T13:11:24.684918","created_date":"2019-05-03T00:00:00"}
