{"id":"https://openalex.org/W2410569288","doi":"https://doi.org/10.1109/allerton.2016.7852343","title":"Asynchrony begets momentum, with an application to deep learning","display_name":"Asynchrony begets momentum, with an application to deep learning","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2410569288","doi":"https://doi.org/10.1109/allerton.2016.7852343","mag":"2410569288"},"language":"en","primary_location":{"id":"doi:10.1109/allerton.2016.7852343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2016.7852343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1605.09774","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088076429","display_name":"Ioannis Mitliagkas","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ioannis Mitliagkas","raw_affiliation_strings":["Dept. of Computer Science, Stanford University","Department of Computer Science, Stanford University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Computer Science, Stanford University, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383731","display_name":"Ce Zhang","orcid":"https://orcid.org/0000-0002-8105-7505"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ce Zhang","raw_affiliation_strings":["Dept. of Computer Science, ETH, Zurich","Department of Computer Science, ETH Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, ETH, Zurich","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Department of Computer Science, ETH Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048870398","display_name":"Stefan Hadjis","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Hadjis","raw_affiliation_strings":["Dept. of Computer Science, Stanford University","Department of Computer Science, Stanford University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Computer Science, Stanford University, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103852640","display_name":"Christopher R\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Re","raw_affiliation_strings":["Dept. of Computer Science, Stanford University","Department of Computer Science, Stanford University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Computer Science, Stanford University, United States","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"997","last_page":"1004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998999834060669,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/asynchrony","display_name":"Asynchrony (computer programming)","score":0.9837825298309326},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7617965936660767},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.6830816268920898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6531780958175659},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5615604519844055},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5356547236442566},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4893724322319031},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.48236554861068726},{"id":"https://openalex.org/keywords/queueing-theory","display_name":"Queueing theory","score":0.4522840678691864},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38625240325927734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36367228627204895},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08216506242752075}],"concepts":[{"id":"https://openalex.org/C2779019669","wikidata":"https://www.wikidata.org/wiki/Q25203946","display_name":"Asynchrony (computer programming)","level":3,"score":0.9837825298309326},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7617965936660767},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.6830816268920898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6531780958175659},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5615604519844055},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5356547236442566},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4893724322319031},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.48236554861068726},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.4522840678691864},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38625240325927734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36367228627204895},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08216506242752075},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/allerton.2016.7852343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2016.7852343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1605.09774","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1605.09774","pdf_url":"https://arxiv.org/pdf/1605.09774","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},{"id":"mag:2410569288","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1605.09774v2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1605.09774","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1605.09774","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1605.09774","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1605.09774","pdf_url":"https://arxiv.org/pdf/1605.09774","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2410569288.pdf","grobid_xml":"https://content.openalex.org/works/W2410569288.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W114517082","https://openalex.org/W809736386","https://openalex.org/W1442374986","https://openalex.org/W1788418780","https://openalex.org/W1811750039","https://openalex.org/W1988720110","https://openalex.org/W2001905757","https://openalex.org/W2034996255","https://openalex.org/W2064675550","https://openalex.org/W2091825929","https://openalex.org/W2336650964","https://openalex.org/W2339765813","https://openalex.org/W2436522418","https://openalex.org/W2951781666","https://openalex.org/W2953384591","https://openalex.org/W2962952793","https://openalex.org/W2963792515","https://openalex.org/W6604254268","https://openalex.org/W6628377381","https://openalex.org/W6638214083","https://openalex.org/W6638989972","https://openalex.org/W6684191040","https://openalex.org/W6684859321","https://openalex.org/W6687107172","https://openalex.org/W6703420464","https://openalex.org/W6713134421","https://openalex.org/W6718307486","https://openalex.org/W6727249380","https://openalex.org/W6764309476"],"related_works":["https://openalex.org/W2963792515","https://openalex.org/W2168231600","https://openalex.org/W2951781666","https://openalex.org/W2194775991","https://openalex.org/W2336650964","https://openalex.org/W1522301498","https://openalex.org/W2436522418","https://openalex.org/W2146502635","https://openalex.org/W2108598243","https://openalex.org/W2907225497","https://openalex.org/W2922371350","https://openalex.org/W2770522929","https://openalex.org/W2787477569","https://openalex.org/W2926417365","https://openalex.org/W3113711659","https://openalex.org/W2122491152","https://openalex.org/W2767624189","https://openalex.org/W3199071121","https://openalex.org/W3011428993","https://openalex.org/W3094709024"],"abstract_inverted_index":{"Asynchronous":[0],"methods":[1,172],"are":[2],"widely":[3],"used":[4,78],"in":[5,26,70,92],"deep":[6,57,80,93,190],"learning,":[7],"but":[8],"have":[9,173],"limited":[10],"theoretical":[11],"justification":[12],"when":[13,135,183],"applied":[14],"to":[15,38,56],"non-convex":[16],"problems.":[17],"We":[18,60,153],"show":[19],"that":[20,62,75,110,128,155],"running":[21],"stochastic":[22],"gradient":[23],"descent":[24],"(SGD)":[25],"an":[27],"asynchronous":[28,171,184],"manner":[29],"can":[30,164],"be":[31,98,165],"viewed":[32],"as":[33],"adding":[34],"a":[35,63,71,85,156],"momentum-like":[36],"term":[37],"the":[39,49,111,118,130,148],"SGD":[40],"iteration.":[41],"Our":[42],"result":[43,178],"does":[44],"not":[45],"assume":[46],"convexity":[47],"of":[48,67,73,113,139,146,151],"objective":[50],"function,":[51],"so":[52],"it":[53],"is":[54,76,127,133,186],"applicable":[55],"learning":[58,81,94,191],"systems.":[59,192],"observe":[61],"standard":[64],"queuing":[65,88],"model":[66],"asynchrony":[68,91,114],"results":[69],"form":[72],"momentum":[74,131,163],"commonly":[77],"by":[79],"practitioners.":[82],"This":[83],"forges":[84],"link":[86],"between":[87],"theory":[89,143],"and":[90],"systems,":[95],"which":[96],"could":[97],"useful":[99],"for":[100,189],"systems":[101],"builders.":[102],"For":[103],"convolutional":[104],"neural":[105],"networks,":[106],"we":[107],"experimentally":[108],"validate":[109],"degree":[112],"directly":[115],"correlates":[116],"with":[117],"momentum,":[119],"confirming":[120],"our":[121,142],"main":[122],"result.":[123],"An":[124],"important":[125,134],"implication":[126],"tuning":[129],"parameter":[132],"considering":[136],"different":[137],"levels":[138],"asynchrony.":[140,152,169],"Furthermore,":[141],"suggests":[144],"ways":[145],"counter-acting":[147],"adverse":[149],"effects":[150],"see":[154],"simple":[157],"mechanism":[158],"like":[159],"using":[160],"negative":[161],"algorithmic":[162],"beneficial":[166],"under":[167],"high":[168],"Since":[170],"better":[174],"hardware":[175],"efficiency,":[176],"this":[177],"may":[179],"shed":[180],"light":[181],"on":[182],"execution":[185],"more":[187],"efficient":[188]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}