{"id":"https://openalex.org/W2787481791","doi":"https://doi.org/10.1109/ita.2018.8503173","title":"On the Insufficiency of Existing Momentum Schemes for Stochastic Optimization","display_name":"On the Insufficiency of Existing Momentum Schemes for Stochastic Optimization","publication_year":2018,"publication_date":"2018-02-01","ids":{"openalex":"https://openalex.org/W2787481791","doi":"https://doi.org/10.1109/ita.2018.8503173","mag":"2787481791"},"language":"en","primary_location":{"id":"doi:10.1109/ita.2018.8503173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ita.2018.8503173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Information Theory and Applications Workshop (ITA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1803.05591","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057958491","display_name":"Rahul Kidambi","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Rahul Kidambi","raw_affiliation_strings":["Tsinghua University","Cornell University, Ithaca, United States"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Cornell University, Ithaca, United States","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007012613","display_name":"Praneeth Netrapalli","orcid":"https://orcid.org/0000-0003-3863-6162"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Praneeth Netrapalli","raw_affiliation_strings":["Beihang University, Beijing, China","Microsoft (United States), Redmond, United States"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101633144","display_name":"Prateek Jain","orcid":"https://orcid.org/0000-0002-9233-5160"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Prateek Jain","raw_affiliation_strings":["Tsinghua University","Microsoft (United States), Redmond, United States"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108381794","display_name":"Sham M. Kakade","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Sham Kakade","raw_affiliation_strings":["Tsinghua University","University of Washington, Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"University of Washington, Seattle, United States","institution_ids":["https://openalex.org/I58610484","https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057958491"],"corresponding_institution_ids":["https://openalex.org/I205783295","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.0154,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81887547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9945999979972839,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9883000254631042,"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/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.8199785947799683},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.597559928894043},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.5522558093070984},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4913555681705475},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.44100522994995117},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4353315532207489},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.4255872964859009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37167876958847046},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3142457604408264},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1598207652568817}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8199785947799683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.597559928894043},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.5522558093070984},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4913555681705475},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.44100522994995117},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4353315532207489},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.4255872964859009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37167876958847046},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3142457604408264},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1598207652568817},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ita.2018.8503173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ita.2018.8503173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Information Theory and Applications Workshop (ITA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.05591","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.05591","pdf_url":"https://arxiv.org/pdf/1803.05591","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":null,"raw_type":"text"},{"id":"mag:2787481791","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1803.05591.pdf","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.1803.05591","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1803.05591","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1803.05591","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.05591","pdf_url":"https://arxiv.org/pdf/1803.05591","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306854","display_name":"Washington Research Foundation","ror":"https://ror.org/00hasdx88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2787481791.pdf","grobid_xml":"https://content.openalex.org/works/W2787481791.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1957482736","https://openalex.org/W1988720110","https://openalex.org/W1994616650","https://openalex.org/W2045453101","https://openalex.org/W2045744861","https://openalex.org/W2095984592","https://openalex.org/W2100495367","https://openalex.org/W2120350480","https://openalex.org/W2124541940","https://openalex.org/W2124768887","https://openalex.org/W2135482703","https://openalex.org/W2161449099","https://openalex.org/W2168909589","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2523060838","https://openalex.org/W2530874098","https://openalex.org/W2608239888","https://openalex.org/W2952594493","https://openalex.org/W6604254268","https://openalex.org/W6608133726","https://openalex.org/W6616617004","https://openalex.org/W6617009369","https://openalex.org/W6631190155","https://openalex.org/W6640920075","https://openalex.org/W6658086432","https://openalex.org/W6676105031","https://openalex.org/W6677106874","https://openalex.org/W6683107984","https://openalex.org/W6691563341","https://openalex.org/W6729595453","https://openalex.org/W6739170280","https://openalex.org/W6744060662","https://openalex.org/W6761030284","https://openalex.org/W6763749585"],"related_works":["https://openalex.org/W2962795635","https://openalex.org/W3210267625","https://openalex.org/W2963208657","https://openalex.org/W2750685566","https://openalex.org/W3024569256","https://openalex.org/W1988720110","https://openalex.org/W3037950432","https://openalex.org/W1629097610","https://openalex.org/W3178427280","https://openalex.org/W3188854175","https://openalex.org/W3035689649","https://openalex.org/W2969133367","https://openalex.org/W2963520461","https://openalex.org/W2899874324","https://openalex.org/W2901831961","https://openalex.org/W2913126955","https://openalex.org/W2886849295","https://openalex.org/W2996927210","https://openalex.org/W2894692220","https://openalex.org/W3005981462"],"abstract_inverted_index":{"Momentum":[0],"based":[1,203],"stochastic":[2,38,65,85,201],"gradient":[3,13,39,51,79,92],"methods":[4,46,80,117],"such":[5],"as":[6,31,194],"heavy":[7],"ball":[8],"(HB)":[9],"and":[10,26,188,228],"Nesterov's":[11,211],"accelerated":[12],"descent":[14,40,52],"(NAG)":[15],"method":[16],"are":[17,61,81,111,161],"widely":[18],"used":[19],"in":[20,83,95,133,216],"practice":[21],"for":[22,54,70],"training":[23],"deep":[24],"networks":[25],"other":[27],"supervised":[28],"learning":[29],"models,":[30],"they":[32,87,138],"often":[33],"provide":[34],"significant":[35],"improvements":[36,49],"over":[37,50,185,225],"(SGD).":[41],"In":[42,63],"general,":[43],"\u201cfast":[44],"gradient\u201d":[45],"have":[47],"provable":[48],"only":[53],"the":[55,59,64,67,84,122,177],"deterministic":[56],"case,":[57,66,86],"where":[58,115],"gradients":[60],"exact.":[62],"popular":[68,208],"explanations":[69],"their":[71,90],"wide":[72],"applicability":[73],"is":[74,196],"that":[75,109,154,220],"when":[76],"these":[77,116],"fast":[78],"applied":[82],"partially":[88],"mimic":[89],"exact":[91],"counterparts,":[93],"resulting":[94],"some":[96],"practical":[97,158],"gain.":[98],"This":[99,191],"work":[100,168],"provides":[101,169],"a":[102,162,170,197,205],"counterpoint":[103],"to":[104,199],"this":[105,167,217],"belief":[106],"by":[107],"proving":[108],"there":[110],"simple":[112,198],"problem":[113,130,181],"instances":[114,131],"cannot":[118],"outperform":[119],"SGD":[120],"despite":[121],"best":[123],"setting":[124],"of":[125,164,180,210],"its":[126],"parameters.":[127],"These":[128,147],"negative":[129],"are,":[132],"an":[134],"informal":[135],"sense,":[136],"generic;":[137],"do":[139],"not":[140],"look":[141],"like":[142],"carefully":[143],"constructed":[144],"pathological":[145],"instances.":[146],"results":[148,215],"suggest":[149],"(along":[150],"with":[151],"empirical":[152,214],"evidence)":[153],"HB":[155],"or":[156],"NAG's":[157],"performance":[159,223],"gains":[160,224],"by-product":[163],"minibatching.":[165],"Furthermore,":[166],"viable":[171],"(and":[172],"provable)":[173],"alternative,":[174],"which,":[175],"on":[176,204],"same":[178],"set":[179],"instances,":[182],"significantly":[183],"improves":[184],"HB,":[186,226],"NAG,":[187,227],"SGD's":[189],"performance.":[190],"algorithm,":[192,202],"denoted":[193],"ASGD,":[195],"implement":[200],"relatively":[206],"less":[207],"version":[209],"AGD.":[212],"Extensive":[213],"paper":[218],"show":[219],"ASGD":[221],"has":[222],"SGD.":[229]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}