{"id":"https://openalex.org/W2055334101","doi":"https://doi.org/10.1145/2783258.2783355","title":"Stochastic Divergence Minimization for Online Collapsed Variational Bayes Zero Inference of Latent Dirichlet Allocation","display_name":"Stochastic Divergence Minimization for Online Collapsed Variational Bayes Zero Inference of Latent Dirichlet Allocation","publication_year":2015,"publication_date":"2015-08-07","ids":{"openalex":"https://openalex.org/W2055334101","doi":"https://doi.org/10.1145/2783258.2783355","mag":"2055334101"},"language":"en","primary_location":{"id":"doi:10.1145/2783258.2783355","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2783258.2783355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5060421432","display_name":"Issei Sato","orcid":"https://orcid.org/0000-0002-5066-1435"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Issei Sato","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020912760","display_name":"Hiroshi Nakagawa","orcid":"https://orcid.org/0000-0002-3024-9136"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Nakagawa","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1035","last_page":"1044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9998999834060669,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9815999865531921,"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":0.9805999994277954,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.872879147529602},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6521922945976257},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6254461407661438},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5195094347000122},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.5091549754142761},{"id":"https://openalex.org/keywords/dirichlet-process","display_name":"Dirichlet process","score":0.49159106612205505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48034727573394775},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.4557492434978485},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.4491012394428253},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4022616446018219},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.39879944920539856},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3815649747848511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2956061363220215},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.26348960399627686},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.21628767251968384}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.872879147529602},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6521922945976257},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6254461407661438},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5195094347000122},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.5091549754142761},{"id":"https://openalex.org/C2781280628","wikidata":"https://www.wikidata.org/wiki/Q5280766","display_name":"Dirichlet process","level":3,"score":0.49159106612205505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48034727573394775},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4557492434978485},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.4491012394428253},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4022616446018219},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39879944920539856},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3815649747848511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2956061363220215},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.26348960399627686},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.21628767251968384},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2783258.2783355","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2783258.2783355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W1520168181","https://openalex.org/W1530235965","https://openalex.org/W1547510099","https://openalex.org/W1880262756","https://openalex.org/W1989879829","https://openalex.org/W1994616650","https://openalex.org/W2001082470","https://openalex.org/W2001975024","https://openalex.org/W2017114036","https://openalex.org/W2042574171","https://openalex.org/W2054333436","https://openalex.org/W2061144551","https://openalex.org/W2072169887","https://openalex.org/W2073300377","https://openalex.org/W2103587173","https://openalex.org/W2108456278","https://openalex.org/W2110829452","https://openalex.org/W2112081648","https://openalex.org/W2130428211","https://openalex.org/W2146341620","https://openalex.org/W2150731624","https://openalex.org/W2157381218","https://openalex.org/W2157906684","https://openalex.org/W2158266063","https://openalex.org/W2161353674","https://openalex.org/W2165599843","https://openalex.org/W2317988884","https://openalex.org/W2559997609","https://openalex.org/W2597289420","https://openalex.org/W2604272474","https://openalex.org/W2618735189","https://openalex.org/W2950182411","https://openalex.org/W2950601375","https://openalex.org/W2950770596","https://openalex.org/W3120740533"],"related_works":["https://openalex.org/W2891616219","https://openalex.org/W2796920963","https://openalex.org/W2497860580","https://openalex.org/W153004028","https://openalex.org/W1902157726","https://openalex.org/W3204672119","https://openalex.org/W2393894849","https://openalex.org/W197558907","https://openalex.org/W2172796364","https://openalex.org/W3122449418"],"abstract_inverted_index":{"The":[0,140],"collapsed":[1,21],"variational":[2,9],"Bayes":[3],"zero":[4],"(CVB0)":[5],"inference":[6,10,29,66,77,94,122,147,156],"is":[7,30,55,62,148],"a":[8,47],"improved":[11],"by":[12,95],"marginalizing":[13],"out":[14],"parameters,":[15],"the":[16,20,27,31,50,58,64,74,86,91,97,117,120,126,132,136,144,153],"same":[17],"as":[18],"with":[19,102],"Gibbs":[22],"sampler.":[23],"A":[24,34,70],"drawback":[25],"of":[26,53,60,73,110,119,125,135,143,152],"CVB0":[28,65,75,121],"memory":[32],"requirements.":[33],"probability":[35],"vector":[36],"must":[37],"be":[38,106],"maintained":[39],"for":[40,43],"latent":[41],"topics":[42,61],"every":[44],"token":[45],"in":[46,108,123,157],"corpus.":[48],"When":[49],"total":[51],"number":[52,59],"tokens":[54],"N":[56],"and":[57],"K,":[63],"requires":[67],"\u039f(NK)":[68,80],"memory.":[69],"stochastic":[71,98],"approximation":[72],"(SCVB0)":[76],"can":[78,105],"reduce":[79],"to":[81,131],"\u039f(VK),":[82],"where":[83],"V":[84],"denotes":[85],"vocabulary":[87],"size.":[88],"We":[89,114],"reformulate":[90],"existing":[92],"SCVB0":[93,146,155],"using":[96],"divergence":[99],"minimization":[100],"algorithm,":[101],"which":[103,129],"convergence":[104,112],"analyzed":[107],"terms":[109,124],"Martingale":[111],"theory.":[113],"also":[115],"reveal":[116],"property":[118],"leave-one-out":[127],"perplexity,":[128],"leads":[130],"estimation":[133],"algorithm":[134],"Dirichlet":[137],"distribution":[138],"parameters.":[139],"predictive":[141],"performance":[142],"propose":[145],"better":[149],"than":[150],"that":[151],"original":[154],"four":[158],"datasets.":[159]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}