{"id":"https://openalex.org/W2182420680","doi":"https://doi.org/10.48550/arxiv.1406.4580","title":"Primitives for Dynamic Big Model Parallelism","display_name":"Primitives for Dynamic Big Model Parallelism","publication_year":2014,"publication_date":"2014-06-18","ids":{"openalex":"https://openalex.org/W2182420680","doi":"https://doi.org/10.48550/arxiv.1406.4580","mag":"2182420680"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1406.4580","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1406.4580","pdf_url":"https://arxiv.org/pdf/1406.4580","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1406.4580","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102015904","display_name":"Seunghak Lee","orcid":"https://orcid.org/0000-0002-8030-7138","observed_orcids":["https://orcid.org/0000-0002-8030-7138"]},"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":false,"raw_author_name":"Lee, Seunghak","raw_affiliation_strings":["School of Computer Science Carnegie Mellon University , Pittsburgh , PA , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science Carnegie Mellon University , Pittsburgh , PA , U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113847826","display_name":"Jin Kyu Kim","orcid":null,"observed_orcids":[]},"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":false,"raw_author_name":"Kim, Jin Kyu","raw_affiliation_strings":["School of Computer Science Carnegie Mellon University , Pittsburgh , PA , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science Carnegie Mellon University , Pittsburgh , PA , U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023132445","display_name":"Xun Zheng","orcid":null,"observed_orcids":[]},"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":false,"raw_author_name":"Zheng, Xun","raw_affiliation_strings":["School of Computer Science Carnegie Mellon University , Pittsburgh , PA , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science Carnegie Mellon University , Pittsburgh , PA , U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012361506","display_name":"Qirong Ho","orcid":null,"observed_orcids":[]},"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":false,"raw_author_name":"Ho, Qirong","raw_affiliation_strings":["School of Computer Science Carnegie Mellon University , Pittsburgh , PA , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science Carnegie Mellon University , Pittsburgh , PA , U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041431830","display_name":"Garth A. Gibson","orcid":"https://orcid.org/0000-0002-6656-7080","observed_orcids":["https://orcid.org/0000-0002-6656-7080"]},"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":false,"raw_author_name":"Gibson, Garth A.","raw_affiliation_strings":["School of Computer Science Carnegie Mellon University , Pittsburgh , PA , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science Carnegie Mellon University , Pittsburgh , PA , U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009547049","display_name":"Eric P. Xing","orcid":"https://orcid.org/0009-0005-9158-4201","observed_orcids":["https://orcid.org/0009-0005-9158-4201","https://orcid.org/0000-0002-3683-4280"]},"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":false,"raw_author_name":"Xing, Eric P.","raw_affiliation_strings":["School of Computer Science Carnegie Mellon University , Pittsburgh , PA , U.S.A","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science Carnegie Mellon University , Pittsburgh , PA , U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.5435000061988831,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.5435000061988831,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.2915000021457672,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.07569999992847443,"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/distributed-learning","display_name":"distributed learning","score":0.8339999914169312},{"id":"https://openalex.org/keywords/model-partitioning","display_name":"model partitioning","score":0.6819999814033508},{"id":"https://openalex.org/keywords/update-scheduling","display_name":"update scheduling","score":0.9200000166893005},{"id":"https://openalex.org/keywords/memory-efficiency","display_name":"memory efficiency","score":0.9039999842643738},{"id":"https://openalex.org/keywords/topic-modeling","display_name":"topic modeling","score":0.8169999718666077},{"id":"https://openalex.org/keywords/matrix-factorization","display_name":"matrix factorization","score":1.0},{"id":"https://openalex.org/keywords/lasso","display_name":"LASSO","score":0.6869999766349792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8811812400817871},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6797187328338623},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.54032301902771},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.49584874510765076},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.45902806520462036},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.4583948850631714},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.42228174209594727},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.3859562873840332},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37872540950775146},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36313220858573914},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.32974952459335327},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24549847841262817},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.10831183195114136},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1406.4580","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1406.4580","pdf_url":"https://arxiv.org/pdf/1406.4580","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,"listed_in":[],"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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.747.3360","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.747.3360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1406.4580.pdf","raw_type":"text"},{"id":"doi:10.48550/arxiv.1406.4580","doi":"https://doi.org/10.48550/arxiv.1406.4580","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1406.4580","pdf_url":null,"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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1406.4580","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1406.4580","pdf_url":"https://arxiv.org/pdf/1406.4580","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2182420680.pdf","grobid_xml":"https://content.openalex.org/works/W2182420680.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W22572007","https://openalex.org/W1511814458","https://openalex.org/W1880262756","https://openalex.org/W1980147176","https://openalex.org/W2001082470","https://openalex.org/W2020098476","https://openalex.org/W2056636001","https://openalex.org/W2096544401","https://openalex.org/W2114643899","https://openalex.org/W2116137244","https://openalex.org/W2118047185","https://openalex.org/W2132737349","https://openalex.org/W2133233009","https://openalex.org/W2135046866","https://openalex.org/W2138996412","https://openalex.org/W2150731624","https://openalex.org/W2166706236","https://openalex.org/W2168231600","https://openalex.org/W2170616854","https://openalex.org/W2173213060","https://openalex.org/W2184628147","https://openalex.org/W2189465200","https://openalex.org/W2341535507","https://openalex.org/W2395355800","https://openalex.org/W2962727278","https://openalex.org/W2963707635"],"related_works":["https://openalex.org/W6903545278","https://openalex.org/W2335835108","https://openalex.org/W1497213868","https://openalex.org/W2119391823","https://openalex.org/W7098588448","https://openalex.org/W2415005847","https://openalex.org/W4407741721","https://openalex.org/W2886825742","https://openalex.org/W52367139","https://openalex.org/W4411403514"],"abstract_inverted_index":{"When":[0],"training":[1,29],"large":[2,23],"machine":[3,13],"learning":[4],"models":[5],"with":[6,36],"many":[7],"variables":[8,105],"or":[9,79],"parameters,":[10],"a":[11,32,87],"single":[12],"is":[14,42],"often":[15],"inadequate":[16],"since":[17],"the":[18,130],"model":[19,104],"may":[20],"be":[21],"too":[22],"to":[24,43,45,51,73,97,120],"fit":[25],"in":[26,49,83,95,106,136],"memory,":[27,70],"while":[28,71,116],"can":[30,64,80],"take":[31],"long":[33],"time":[34],"even":[35,81],"stochastic":[37],"updates.":[38],"A":[39],"natural":[40],"recourse":[41],"turn":[44],"distributed":[46,69,107],"cluster":[47],"computing,":[48],"order":[50,96],"harness":[52],"additional":[53],"memory":[54,114],"and":[55,100,146],"processors.":[56],"However,":[57],"naive,":[58],"unstructured":[59],"parallelization":[60],"of":[61,68,89,103,132],"ML":[62,108],"algorithms":[63,109,134],"make":[65],"inefficient":[66],"use":[67],"failing":[72],"obtain":[74],"proportional":[75],"convergence":[76,123],"speedups":[77],"-":[78,110],"result":[82],"divergence.":[84],"We":[85,128],"develop":[86],"framework":[88],"primitives":[90],"for":[91,141],"dynamic":[92],"model-parallelism,":[93],"STRADS,":[94],"explore":[98],"partitioning":[99],"update":[101],"scheduling":[102],"thus":[111],"improving":[112],"their":[113],"efficiency":[115],"presenting":[117],"new":[118],"opportunities":[119],"speed":[121],"up":[122],"without":[124],"compromising":[125],"inference":[126],"correctness.":[127],"demonstrate":[129],"efficacy":[131],"model-parallel":[133],"implemented":[135],"STRADS":[137],"versus":[138],"popular":[139],"implementations":[140],"Topic":[142],"Modeling,":[143],"Matrix":[144],"Factorization":[145],"Lasso.":[147]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}