{"id":"https://openalex.org/W2112395999","doi":"https://doi.org/10.1145/1390156.1390305","title":"Fully distributed EM for very large datasets","display_name":"Fully distributed EM for very large datasets","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2112395999","doi":"https://doi.org/10.1145/1390156.1390305","mag":"2112395999"},"language":"en","primary_location":{"id":"doi:10.1145/1390156.1390305","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th international conference on Machine learning - ICML '08","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/A5111364097","display_name":"Jason Wolfe","orcid":null},"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":true,"raw_author_name":"Jason Wolfe","raw_affiliation_strings":["University of California, Berkeley, CA","University of California: Berkeley, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California: Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039365507","display_name":"Aria Haghighi","orcid":"https://orcid.org/0000-0002-4997-0353"},"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,"raw_author_name":"Aria Haghighi","raw_affiliation_strings":["University of California, Berkeley, CA","University of California: Berkeley, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California: Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004921249","display_name":"Dan Klein","orcid":"https://orcid.org/0000-0002-8881-1902"},"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,"raw_author_name":"Dan Klein","raw_affiliation_strings":["University of California, Berkeley, CA","University of California: Berkeley, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California: Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111364097"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":10.6354,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":{"value":0.98716612,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1184","last_page":"1191"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8425852060317993},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.756463885307312},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6563448905944824},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6062503457069397},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.5467178225517273},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.5341400504112244},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4478500783443451},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4387109875679016},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42448610067367554},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35614222288131714},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2868170738220215},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.22245624661445618},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08963906764984131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8425852060317993},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.756463885307312},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6563448905944824},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6062503457069397},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.5467178225517273},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.5341400504112244},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4478500783443451},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4387109875679016},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42448610067367554},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35614222288131714},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2868170738220215},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.22245624661445618},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08963906764984131},{"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/1390156.1390305","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th international conference on Machine learning - ICML '08","raw_type":"proceedings-article"},{"id":"pmh:oai:berkeley.edu:28722-bk0000m747f","is_oa":false,"landing_page_url":"http://techreports.lib.berkeley.edu/accessPages/EECS-2007-178.html","pdf_url":null,"source":{"id":"https://openalex.org/S7407050879","display_name":"UC Berkeley","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"technical reports"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.116.5244","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.116.5244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~jawolfe/pubs/07-tr-em.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.141.2214","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.2214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~aria42/pubs/icml08-distributedem.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.8023","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.8023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://icml2008.cs.helsinki.fi/papers/311.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.218.3223","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.218.3223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~jawolfe/pubs/08-icml-em.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1479971791","https://openalex.org/W1880262756","https://openalex.org/W2006969979","https://openalex.org/W2049633694","https://openalex.org/W2109722477","https://openalex.org/W2150102617","https://openalex.org/W2153029569","https://openalex.org/W2158307424","https://openalex.org/W2159080219","https://openalex.org/W2173213060"],"related_works":["https://openalex.org/W2086397253","https://openalex.org/W2133122801","https://openalex.org/W600422426","https://openalex.org/W2046435967","https://openalex.org/W2007156430","https://openalex.org/W2170882281","https://openalex.org/W3081478936","https://openalex.org/W4231775656","https://openalex.org/W2785612136","https://openalex.org/W1985727224"],"abstract_inverted_index":{"In":[0],"EM":[1,47],"and":[2,80],"related":[3],"algorithms,":[4],"E-step":[5],"computations":[6],"distribute":[7],"easily,":[8],"because":[9],"data":[10,19],"items":[11],"are":[12],"independent":[13],"given":[14],"parameters.":[15],"For":[16],"very":[17],"large":[18],"sets,":[20],"however,":[21],"even":[22],"storing":[23],"all":[24],"of":[25],"the":[26,33,45],"parameters":[27,54],"in":[28],"a":[29,40,65,72],"single":[30],"node":[31,50],"for":[32],"M-step":[34],"can":[35],"be":[36],"impractical.":[37],"We":[38,68],"present":[39],"framework":[41],"that":[42],"fully":[43],"distributes":[44],"entire":[46],"procedure.":[48],"Each":[49],"interacts":[51],"only":[52],"with":[53],"relevant":[55],"to":[56,61],"its":[57],"data,":[58],"sending":[59],"messages":[60],"other":[62],"nodes":[63],"along":[64],"junction-tree":[66],"topology.":[67],"demonstrate":[69],"improvements":[70],"over":[71],"MapReduce":[73],"topology,":[74],"on":[75],"two":[76],"tasks:":[77],"word":[78],"alignment":[79],"topic":[81],"modeling.":[82]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}