{"id":"https://openalex.org/W2052261215","doi":"https://doi.org/10.1145/2623330.2623756","title":"Reducing the sampling complexity of topic models","display_name":"Reducing the sampling complexity of topic models","publication_year":2014,"publication_date":"2014-08-22","ids":{"openalex":"https://openalex.org/W2052261215","doi":"https://doi.org/10.1145/2623330.2623756","mag":"2052261215"},"language":"en","primary_location":{"id":"doi:10.1145/2623330.2623756","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"article","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/A5053182948","display_name":"Aaron Q. Li","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aaron Q. Li","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009154893","display_name":"Amr Ahmed","orcid":"https://orcid.org/0000-0002-7749-7911"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amr Ahmed","raw_affiliation_strings":["Google Inc., Mountain View, CA, USA","Google Inc., Mountain View, CA USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104067009","display_name":"Sujith Ravi","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sujith Ravi","raw_affiliation_strings":["Google Inc., Mountain View, CA, USA","Google Inc., Mountain View, CA USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000245150","display_name":"Alexander J. Smola","orcid":"https://orcid.org/0000-0002-7963-4721"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander J. Smola","raw_affiliation_strings":["Carnegie Mellon University and Google Inc., Pittsburgh, PA, USA","Carnegie Mellon University and Google Inc., Pittsburgh, PA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University and Google Inc., Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University and Google Inc., Pittsburgh, PA, USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053182948"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":40.5926,"has_fulltext":false,"cited_by_count":225,"citation_normalized_percentile":{"value":0.99824496,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"891","last_page":"900"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.7571280002593994},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7205030918121338},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7181674242019653},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5813406705856323},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5800944566726685},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5085242986679077},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4985167980194092},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4612976014614105},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4405743479728699},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.43573760986328125},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4309818744659424},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3871643543243408},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37740084528923035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36768701672554016},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3629758358001709},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16546285152435303},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.15773773193359375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7571280002593994},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7205030918121338},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7181674242019653},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5813406705856323},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5800944566726685},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5085242986679077},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4985167980194092},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4612976014614105},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4405743479728699},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43573760986328125},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4309818744659424},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3871643543243408},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37740084528923035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36768701672554016},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3629758358001709},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16546285152435303},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.15773773193359375},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2623330.2623756","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.675.8158","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.675.8158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sravi.org/pubs/fastlda-kdd2014.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1132490312","display_name":null,"funder_award_id":"Faculty Research Grant","funder_id":"https://openalex.org/F4320307102","funder_display_name":"Intel Corporation"},{"id":"https://openalex.org/G6987871453","display_name":null,"funder_award_id":"Faculty Research Grant","funder_id":"https://openalex.org/F4320309327","funder_display_name":"Google"}],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W203054622","https://openalex.org/W1866637071","https://openalex.org/W1880262756","https://openalex.org/W1915058860","https://openalex.org/W2001082470","https://openalex.org/W2041517243","https://openalex.org/W2053725995","https://openalex.org/W2065221212","https://openalex.org/W2080972498","https://openalex.org/W2087309226","https://openalex.org/W2110591510","https://openalex.org/W2115529864","https://openalex.org/W2130416410","https://openalex.org/W2145768976","https://openalex.org/W2150286230","https://openalex.org/W2150731624","https://openalex.org/W2158266063","https://openalex.org/W2161194249","https://openalex.org/W2163021329","https://openalex.org/W2187741934","https://openalex.org/W2952905572","https://openalex.org/W3120740533","https://openalex.org/W6639973174","https://openalex.org/W6664261499","https://openalex.org/W6676781583","https://openalex.org/W6681597451","https://openalex.org/W6683603713","https://openalex.org/W6684578138"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Inference":[0],"in":[1,53,61],"topic":[2],"models":[3,64,84],"typically":[4],"involves":[5],"a":[6,79],"sampling":[7],"step":[8],"to":[9,78],"associate":[10],"latent":[11],"variables":[12],"with":[13,45],"observations.":[14],"Unfortunately":[15],"the":[16,22,46,54],"generative":[17],"model":[18],"loses":[19],"sparsity":[20],"as":[21,86],"amount":[23],"of":[24,48,72,82],"data":[25],"increases,":[26],"requiring":[27],"O(k)":[28],"operations":[29],"per":[30],"word":[31],"for":[32],"k":[33],"topics.":[34],"In":[35],"this":[36],"paper":[37],"we":[38],"propose":[39],"an":[40,70],"algorithm":[41],"which":[42],"scales":[43],"linearly":[44],"number":[47],"actually":[49],"instantiated":[50],"topics":[51],"kd":[52,65],"document.":[55],"For":[56],"large":[57],"document":[58],"collections":[59],"and":[60,89],"structured":[62],"hierarchical":[63],"ll":[66],"k.":[67],"This":[68],"yields":[69],"order":[71],"magnitude":[73],"speedup.":[74],"Our":[75],"method":[76],"applies":[77],"wide":[80],"variety":[81],"statistical":[83],"such":[85],"PDP":[87],"[16,4]":[88],"HDP":[90],"[19].":[91]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":33},{"year":2018,"cited_by_count":30},{"year":2017,"cited_by_count":36},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":32},{"year":2014,"cited_by_count":5}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}