{"id":"https://openalex.org/W2270588982","doi":"https://doi.org/10.1162/neco_a_00892","title":"A Universal Approximation Theorem for Mixture-of-Experts Models","display_name":"A Universal Approximation Theorem for Mixture-of-Experts Models","publication_year":2016,"publication_date":"2016-09-14","ids":{"openalex":"https://openalex.org/W2270588982","doi":"https://doi.org/10.1162/neco_a_00892","mag":"2270588982","pmid":"https://pubmed.ncbi.nlm.nih.gov/27626962"},"language":"en","primary_location":{"id":"doi:10.1162/neco_a_00892","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_00892","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037340964","display_name":"Hien D. Nguyen","orcid":"https://orcid.org/0000-0002-9958-432X"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Hien D. Nguyen","raw_affiliation_strings":["School of Mathematics and Physics, University of Queensland, Brisbane, Queensland 4072, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Physics, University of Queensland, Brisbane, Queensland 4072, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024982512","display_name":"Luke R. Lloyd\u2010Jones","orcid":"https://orcid.org/0000-0002-0229-0625"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Luke R. Lloyd-Jones","raw_affiliation_strings":["Centre for Neurogenetics and Statistical Genetics, Queensland Brain Institute, University of Queensland, Brisbane, Queensland 4072, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Neurogenetics and Statistical Genetics, Queensland Brain Institute, University of Queensland, Brisbane, Queensland 4072, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057375178","display_name":"Geoffrey J. McLachlan","orcid":"https://orcid.org/0000-0002-5921-3145"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Geoffrey J. McLachlan","raw_affiliation_strings":["School of Mathematics and Physics, University of Queensland, Brisbane, Queensland 4072, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Physics, University of Queensland, Brisbane, Queensland 4072, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5024982512","https://openalex.org/A5037340964","https://openalex.org/A5057375178"],"corresponding_institution_ids":["https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":6.4965,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.96594636,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"28","issue":"12","first_page":"2585","last_page":"2593"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9990000128746033,"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/T10320","display_name":"Neural Networks and Applications","score":0.9990000128746033,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9944000244140625,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9926999807357788,"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/mathematics","display_name":"Mathematics","score":0.7038445472717285},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.6953850984573364},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.5400664806365967},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5290896892547607},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.5129620432853699},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5110958218574524},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.50014328956604},{"id":"https://openalex.org/keywords/sobolev-space","display_name":"Sobolev space","score":0.4970431625843048},{"id":"https://openalex.org/keywords/hypercube","display_name":"Hypercube","score":0.4937816560268402},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47118616104125977},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41808587312698364},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.35318875312805176},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.31578707695007324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27575474977493286},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.26309990882873535},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.25255197286605835}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7038445472717285},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.6953850984573364},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5400664806365967},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5290896892547607},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.5129620432853699},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5110958218574524},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.50014328956604},{"id":"https://openalex.org/C99730327","wikidata":"https://www.wikidata.org/wiki/Q1501536","display_name":"Sobolev space","level":2,"score":0.4970431625843048},{"id":"https://openalex.org/C50820777","wikidata":"https://www.wikidata.org/wiki/Q213723","display_name":"Hypercube","level":2,"score":0.4937816560268402},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47118616104125977},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41808587312698364},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.35318875312805176},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.31578707695007324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27575474977493286},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.26309990882873535},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.25255197286605835},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/neco_a_00892","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_00892","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:27626962","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27626962","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural computation","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1538807145","https://openalex.org/W1579271636","https://openalex.org/W1581352608","https://openalex.org/W1969907345","https://openalex.org/W2025653905","https://openalex.org/W2061155774","https://openalex.org/W2068238590","https://openalex.org/W2070195804","https://openalex.org/W2075273870","https://openalex.org/W2080985899","https://openalex.org/W2085831769","https://openalex.org/W2103496339","https://openalex.org/W2112335378","https://openalex.org/W2115131990","https://openalex.org/W2135879592","https://openalex.org/W2148845857","https://openalex.org/W2150884987","https://openalex.org/W2152619728","https://openalex.org/W2163696743","https://openalex.org/W2168175751","https://openalex.org/W2488678869","https://openalex.org/W2574937674","https://openalex.org/W3105408180","https://openalex.org/W3150304496","https://openalex.org/W4244779605"],"related_works":["https://openalex.org/W4286907761","https://openalex.org/W2916710807","https://openalex.org/W2413588304","https://openalex.org/W3205447645","https://openalex.org/W2009411567","https://openalex.org/W2371629703","https://openalex.org/W2097769911","https://openalex.org/W4286826125","https://openalex.org/W1967359483","https://openalex.org/W2004122589"],"abstract_inverted_index":{"The":[0,15,99],"mixture-of-experts":[1],"(MoE)":[2],"model":[3],"is":[4,21,37,43,52,71],"a":[5,39,53,92],"popular":[6],"neural":[7],"network":[8],"architecture":[9],"for":[10,96,113],"nonlinear":[11,119],"regression":[12],"and":[13,46,120],"classification.":[14],"class":[16,66,75],"of":[17,50,67,76,84],"MoE":[18,68,97,104],"mean":[19,69],"functions":[20,70,79],"known":[22],"to":[23,27,106],"be":[24,89,107],"uniformly":[25],"convergent":[26],"any":[28],"unknown":[29],"target":[30,35],"function,":[31],"assuming":[32],"that":[33,42,47,64],"the":[34,48,65,74],"function":[36],"from":[38,118],"Sobolev":[40],"space":[41],"sufficiently":[44],"differentiable":[45],"domain":[49],"estimation":[51,114],"compact":[54,82],"unit":[55],"hypercube.":[56],"We":[57],"provide":[58],"an":[59],"alternative":[60],"result,":[61],"which":[62],"shows":[63],"dense":[72],"in":[73,109],"all":[77],"continuous":[78],"over":[80],"arbitrary":[81],"domains":[83],"estimation.":[85],"Our":[86],"result":[87],"can":[88],"viewed":[90],"as":[91],"universal":[93],"approximation":[94],"theorem":[95,100],"models.":[98],"we":[101],"present":[102],"allows":[103],"users":[105],"confident":[108],"applying":[110],"such":[111],"models":[112],"when":[115],"data":[116],"arise":[117],"nondifferentiable":[121],"generative":[122],"processes.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}