{"id":"https://openalex.org/W2987203808","doi":"https://doi.org/10.1145/3358960.3379141","title":"Throughput Prediction of Asynchronous SGD in TensorFlow","display_name":"Throughput Prediction of Asynchronous SGD in TensorFlow","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W2987203808","doi":"https://doi.org/10.1145/3358960.3379141","mag":"2987203808"},"language":"en","primary_location":{"id":"doi:10.1145/3358960.3379141","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3358960.3379141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.04650","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhuojin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuojin Li","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wumo Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wumo Yan","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Marco Paolieri","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco Paolieri","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":null,"display_name":"Leana Golubchik","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leana Golubchik","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"521","issue":null,"first_page":"76","last_page":"87"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9912999868392944,"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/asynchronous-communication","display_name":"Asynchronous communication","score":0.736299991607666},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.7114999890327454},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6118000149726868},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6111000180244446},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5501999855041504},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.54830002784729},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44519999623298645},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.4438999891281128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8495000004768372},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.736299991607666},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.7114999890327454},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6118000149726868},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6111000180244446},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5501999855041504},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.54830002784729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48100000619888306},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4611999988555908},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44519999623298645},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4251999855041504},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.30880001187324524},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3000999987125397},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C3832189","wikidata":"https://www.wikidata.org/wiki/Q8588916","display_name":"Models of neural computation","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C24858836","wikidata":"https://www.wikidata.org/wiki/Q844718","display_name":"Theory of computation","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2565000057220459},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3358960.3379141","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3358960.3379141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.04650","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.04650","pdf_url":"https://arxiv.org/pdf/1911.04650","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:1911.04650","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.04650","pdf_url":"https://arxiv.org/pdf/1911.04650","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":[],"awards":[{"id":"https://openalex.org/G1652021713","display_name":null,"funder_award_id":"CNS-1816887, CCF-1763747","funder_id":"https://openalex.org/F4320309856","funder_display_name":"National Youth Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320309856","display_name":"National Youth Science Foundation","ror":"https://ror.org/054yz2f06"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2753713840","https://openalex.org/W2946408574","https://openalex.org/W2964324519","https://openalex.org/W2964350391"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"machine":[1],"learning":[2],"frameworks":[3],"can":[4],"train":[5],"neural":[6,138],"networks":[7],"using":[8,147],"multiple":[9,83,124],"nodes":[10,53,84,148],"in":[11,43,166],"parallel,":[12],"each":[13,96],"computing":[14],"parameter":[15,29,93],"updates":[16,42],"with":[17,123,150,154,176],"stochastic":[18],"gradient":[19],"descent":[20],"(SGD)":[21],"and":[22,35,85,95,106,114,116,142,168],"sharing":[23],"them":[24],"asynchronously":[25],"through":[26],"a":[27,44,60,71],"central":[28],"server.":[30],"Due":[31],"to":[32,62,78],"communication":[33,115],"overhead":[34],"bottlenecks,":[36],"the":[37,50,80,86,92,101,159,169,179],"total":[38],"throughput":[39,65],"of":[40,52,82,88,161,171,178],"SGD":[41],"cluster":[45],"scales":[46],"sublinearly,":[47],"saturating":[48],"as":[49],"number":[51],"increases.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58,109],"present":[59],"solution":[61],"predicting":[63],"training":[64,132],"from":[66,70],"profiling":[67],"traces":[68,120],"collected":[69],"single-node":[72],"configuration.":[73],"Our":[74],"approach":[75,129,173],"is":[76],"able":[77],"model":[79],"interaction":[81],"scheduling":[87],"concurrent":[89],"transmissions":[90],"between":[91,103,112],"server":[94],"node.":[97],"By":[98],"accounting":[99],"for":[100,121,134],"dependencies":[102],"received":[104],"parts":[105],"pending":[107],"computations,":[108],"predict":[110],"overlaps":[111],"computation":[113],"generate":[117],"synthetic":[118],"execution":[119],"configurations":[122],"nodes.":[125],"We":[126,156],"validate":[127],"our":[128,144,172],"on":[130,140,143],"TensorFlow":[131,167],"jobs":[133],"popular":[135],"image":[136],"classification":[137],"networks,":[139],"AWS":[141],"in-house":[145],"cluster,":[146],"equipped":[149],"GPUs":[151],"or":[152],"only":[153],"CPUs.":[155],"also":[157],"investigate":[158],"effects":[160],"data":[162],"transmission":[163,180],"policies":[164],"used":[165],"accuracy":[170],"when":[174],"combined":[175],"optimizations":[177],"schedule.":[181]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2019-11-22T00:00:00"}