{"id":"https://openalex.org/W3109198354","doi":"https://doi.org/10.1109/icca51439.2020.9264458","title":"Convergence of Momentum-Based Stochastic Gradient Descent","display_name":"Convergence of Momentum-Based Stochastic Gradient Descent","publication_year":2020,"publication_date":"2020-10-09","ids":{"openalex":"https://openalex.org/W3109198354","doi":"https://doi.org/10.1109/icca51439.2020.9264458","mag":"3109198354"},"language":"en","primary_location":{"id":"doi:10.1109/icca51439.2020.9264458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control & Automation (ICCA)","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/A5019577419","display_name":"Ruinan Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120485","display_name":"Academy of Mathematics and Systems Science","ror":"https://ror.org/02jkmyk67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210120485"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210095018","display_name":"National Center for Mathematics and Interdisciplinary Sciences","ror":"https://ror.org/00s97k668","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210095018"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruinan Jin","raw_affiliation_strings":["LSC, NCMIS, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China","School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"LSC, NCMIS, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210120485","https://openalex.org/I4210095018","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022886989","display_name":"Xingkang He","orcid":"https://orcid.org/0000-0002-5744-1371"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xingkang He","raw_affiliation_strings":["Division of Decision and Control Systems, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Decision and Control Systems, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019577419"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210095018","https://openalex.org/I4210120485","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.5302,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.73700306,"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":"779","last_page":"784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":1.0,"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":1.0,"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":0.9990000128746033,"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":0.9987000226974487,"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":0.8841991424560547},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7027231454849243},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6598278284072876},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.659318208694458},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.6550557017326355},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5663965940475464},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5466762185096741},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.5459855794906616},{"id":"https://openalex.org/keywords/descent","display_name":"Descent (aeronautics)","score":0.5321886539459229},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5170819759368896},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.47779494524002075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2783297896385193},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24205446243286133},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14634141325950623},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.07448697090148926}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8841991424560547},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7027231454849243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6598278284072876},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.659318208694458},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.6550557017326355},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5663965940475464},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5466762185096741},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.5459855794906616},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.5321886539459229},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5170819759368896},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.47779494524002075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2783297896385193},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24205446243286133},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14634141325950623},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.07448697090148926},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":1,"locations":[{"id":"doi:10.1109/icca51439.2020.9264458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control & Automation (ICCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1501203061","https://openalex.org/W1522301498","https://openalex.org/W1955857676","https://openalex.org/W1980287119","https://openalex.org/W1988720110","https://openalex.org/W1992208280","https://openalex.org/W2025941816","https://openalex.org/W2048417186","https://openalex.org/W2100495367","https://openalex.org/W2142623206","https://openalex.org/W2143612262","https://openalex.org/W2154682027","https://openalex.org/W2163605009","https://openalex.org/W2337540838","https://openalex.org/W2436219157","https://openalex.org/W2515982605","https://openalex.org/W2785791552","https://openalex.org/W2801723110","https://openalex.org/W2963335821","https://openalex.org/W2963433607","https://openalex.org/W6604254268","https://openalex.org/W6631190155","https://openalex.org/W6682774789","https://openalex.org/W6684191040","https://openalex.org/W6703265075","https://openalex.org/W6718220094","https://openalex.org/W6748304459"],"related_works":["https://openalex.org/W2895097035","https://openalex.org/W4286899070","https://openalex.org/W4323366756","https://openalex.org/W3207830353","https://openalex.org/W4285259204","https://openalex.org/W3109198354","https://openalex.org/W3109737792","https://openalex.org/W937081240","https://openalex.org/W2760303966","https://openalex.org/W2964140730"],"abstract_inverted_index":{"With":[0],"the":[1,21,30,37,54,58,65,96],"rapid":[2],"increase":[3],"of":[4,36,109],"data":[5],"amount":[6],"in":[7,53,57,90],"many":[8],"fields,":[9],"such":[10,77],"as":[11,78],"machine":[12,55],"learning":[13,56],"and":[14,51],"networked":[15],"systems,":[16],"optimization-based":[17],"methods":[18],"inevitably":[19],"confront":[20],"computational":[22],"issues,":[23],"which":[24,72],"can":[25],"be":[26],"well":[27],"dealt":[28],"by":[29],"stochastic":[31,40,43],"optimization":[32,41],"strategies.":[33],"As":[34],"one":[35],"most":[38],"fundamental":[39],"algorithms,":[42],"gradient":[44],"descent":[45],"(SGD)":[46],"has":[47],"been":[48],"intensively":[49],"developed":[50],"employed":[52],"past":[59],"decade.":[60],"But":[61],"unfortunately,":[62],"due":[63],"to":[64],"technical":[66],"difficulties,":[67],"other":[68],"SGD":[69,80],"based":[70],"algorithms":[71],"could":[73],"achieve":[74],"better":[75],"performance,":[76],"momentum-based":[79],"(mSGD),":[81],"still":[82],"lack":[83],"theoretical":[84],"basis.":[85],"Based":[86],"on":[87],"this":[88,91],"fact,":[89],"paper,":[92],"we":[93],"prove":[94],"that":[95],"mSGD":[97,110],"algorithm":[98],"is":[99,111],"almost":[100],"surely":[101],"convergent":[102],"at":[103],"each":[104],"trajectory.":[105],"The":[106],"convergence":[107],"rate":[108],"also":[112],"analyzed.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}