{"id":"https://openalex.org/W2952362964","doi":"https://doi.org/10.1109/tpami.2018.2832641","title":"P\u00f3lya Urn Latent Dirichlet Allocation: A Doubly Sparse Massively Parallel Sampler","display_name":"P\u00f3lya Urn Latent Dirichlet Allocation: A Doubly Sparse Massively Parallel Sampler","publication_year":2018,"publication_date":"2018-06-04","ids":{"openalex":"https://openalex.org/W2952362964","doi":"https://doi.org/10.1109/tpami.2018.2832641","mag":"2952362964","pmid":"https://pubmed.ncbi.nlm.nih.gov/29994329"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2018.2832641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2018.2832641","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1704.03581","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037482578","display_name":"Alexander Terenin","orcid":"https://orcid.org/0000-0001-5292-3104"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexander Terenin","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-5292-3104","affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101739005","display_name":"M\u00e5ns Magnusson","orcid":"https://orcid.org/0000-0002-0296-2719"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Mans Magnusson","raw_affiliation_strings":["Link\u00f6ping University, Link\u00f6ping, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-0296-2719","affiliations":[{"raw_affiliation_string":"Link\u00f6ping University, Link\u00f6ping, Sweden","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101569881","display_name":"Leif Jonsson","orcid":"https://orcid.org/0000-0002-8989-0251"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Leif Jonsson","raw_affiliation_strings":["Link\u00f6ping University, Link\u00f6ping, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-8989-0251","affiliations":[{"raw_affiliation_string":"Link\u00f6ping University, Link\u00f6ping, Sweden","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001965218","display_name":"David Draper","orcid":"https://orcid.org/0000-0002-6367-3101"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Draper","raw_affiliation_strings":["University of California, Santa Cruz, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6367-3101","affiliations":[{"raw_affiliation_string":"University of California, Santa Cruz, CA, USA","institution_ids":["https://openalex.org/I185103710"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1066,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.84598442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"41","issue":"7","first_page":"1709","last_page":"1719"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.995199978351593,"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":0.8456259965896606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7967275381088257},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6660258173942566},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.593814492225647},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.5666123032569885},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.49485868215560913},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.49241745471954346},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.46053504943847656},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4531548023223877},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36662209033966064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30275797843933105},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.23884066939353943}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8456259965896606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7967275381088257},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6660258173942566},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.593814492225647},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5666123032569885},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.49485868215560913},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.49241745471954346},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.46053504943847656},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4531548023223877},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36662209033966064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30275797843933105},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.23884066939353943},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2018.2832641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2018.2832641","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:29994329","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29994329","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":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:1704.03581","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.03581","pdf_url":"https://arxiv.org/pdf/1704.03581","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,"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1704.03581","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.03581","pdf_url":"https://arxiv.org/pdf/1704.03581","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,"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":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3226541631","display_name":"Robot-assisterade hastigt bildade kunskapsn\u00e4tverk","funder_award_id":"RIT15-0097","funder_id":"https://openalex.org/F4320320940","funder_display_name":"Stiftelsen f\u00f6r\u00a0Strategisk Forskning"},{"id":"https://openalex.org/G6676580822","display_name":null,"funder_award_id":"RIT 15-0097","funder_id":"https://openalex.org/F4320327257","funder_display_name":"Stiftelsen f\u00f6r Strategisk Forskning"}],"funders":[{"id":"https://openalex.org/F4320320940","display_name":"Stiftelsen f\u00f6r\u00a0Strategisk Forskning","ror":"https://ror.org/044wr7g58"},{"id":"https://openalex.org/F4320327257","display_name":"Stiftelsen f\u00f6r Strategisk Forskning","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1460189015","https://openalex.org/W1515461433","https://openalex.org/W1517590677","https://openalex.org/W1529840045","https://openalex.org/W1609010894","https://openalex.org/W1880262756","https://openalex.org/W1889026943","https://openalex.org/W2001082470","https://openalex.org/W2052261215","https://openalex.org/W2053782355","https://openalex.org/W2063998852","https://openalex.org/W2065221212","https://openalex.org/W2089484716","https://openalex.org/W2090078891","https://openalex.org/W2099064293","https://openalex.org/W2099873701","https://openalex.org/W2107107106","https://openalex.org/W2111565546","https://openalex.org/W2116137244","https://openalex.org/W2130339025","https://openalex.org/W2144100511","https://openalex.org/W2150731624","https://openalex.org/W2153086947","https://openalex.org/W2166851633","https://openalex.org/W2270982769","https://openalex.org/W2294384375","https://openalex.org/W2346321220","https://openalex.org/W2400023812","https://openalex.org/W2487122920","https://openalex.org/W2529865518","https://openalex.org/W2533991995","https://openalex.org/W2610338502","https://openalex.org/W2619463892","https://openalex.org/W2751244547","https://openalex.org/W2752488889","https://openalex.org/W2762323257","https://openalex.org/W2896812011","https://openalex.org/W2953337630","https://openalex.org/W2963254535","https://openalex.org/W2963491860","https://openalex.org/W2963704660","https://openalex.org/W2964215670","https://openalex.org/W3036967870","https://openalex.org/W4231510805","https://openalex.org/W4294562888","https://openalex.org/W4302023333","https://openalex.org/W4385534128","https://openalex.org/W6639619044","https://openalex.org/W6674749460","https://openalex.org/W6675002571","https://openalex.org/W6676274861","https://openalex.org/W6677121468","https://openalex.org/W6679482899","https://openalex.org/W6684578138","https://openalex.org/W6696612008","https://openalex.org/W6704886596","https://openalex.org/W6712601926","https://openalex.org/W6729438250","https://openalex.org/W6736998403","https://openalex.org/W6738064377","https://openalex.org/W6743244572","https://openalex.org/W6743809441","https://openalex.org/W6745656744","https://openalex.org/W6824062597"],"related_works":["https://openalex.org/W2939843948","https://openalex.org/W2914864478","https://openalex.org/W2097627380","https://openalex.org/W2008338582","https://openalex.org/W4291700620","https://openalex.org/W1999586157","https://openalex.org/W22044811","https://openalex.org/W2625329765","https://openalex.org/W2766840109","https://openalex.org/W2352674739"],"abstract_inverted_index":{"Latent":[0],"Dirichlet":[1],"Allocation":[2],"(LDA)":[3],"is":[4,84],"a":[5,71,101,128],"topic":[6,134,150],"model":[7,22],"widely":[8],"used":[9],"in":[10,41,67,105,148],"natural":[11],"language":[12],"processing":[13],"and":[14,43,78,88],"machine":[15],"learning.":[16],"Most":[17],"approaches":[18,49,176],"to":[19,31,50,56,145],"training":[20],"the":[21,57,106,116,149,167],"rely":[23],"on":[24,34,177],"iterative":[25],"algorithms,":[26],"which":[27],"makes":[28],"it":[29],"difficult":[30],"run":[32],"LDA":[33],"big":[35],"corpora":[36],"that":[37,74,81,115,173],"are":[38],"best":[39],"analyzed":[40],"parallel":[42,51],"distributed":[44],"computational":[45],"environments.":[46],"Indeed,":[47],"current":[48],"inference":[52],"either":[53],"don't":[54],"converge":[55],"correct":[58],"posterior":[59],"or":[60],"require":[61],"storage":[62],"of":[63,130,169,174],"large":[64],"dense":[65],"matrices":[66],"memory.":[68],"We":[69,96,113,163],"present":[70],"novel":[72,102],"sampler":[73,83,110],"overcomes":[75],"both":[76,86],"problems,":[77],"we":[79,138],"show":[80],"this":[82],"faster,":[85],"empirically":[87],"theoretically,":[89],"than":[90,159],"previous":[91],"Gibbs":[92],"samplers":[93,154],"for":[94,111,132],"LDA.":[95,112],"do":[97],"so":[98],"by":[99,165],"employing":[100],"P\u00f3lya-urn-based":[103],"approximation":[104,117],"sparse":[107],"partially":[108],"collapsed":[109,153,161],"prove":[114],"error":[118],"vanishes":[119],"with":[120,172],"data":[121],"size,":[122],"making":[123],"our":[124,170],"algorithm":[125,171],"asymptotically":[126],"exact,":[127],"property":[129],"importance":[131],"large-scale":[133],"models.":[135],"In":[136],"addition,":[137],"show,":[139],"via":[140],"an":[141],"explicit":[142],"example,":[143],"that-contrary":[144],"popular":[146],"belief":[147],"modeling":[151],"literature-partially":[152],"can":[155],"be":[156],"more":[157],"efficient":[158],"fully":[160],"samplers.":[162],"conclude":[164],"comparing":[166],"performance":[168],"other":[175],"well-known":[178],"corpora.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}