{"id":"https://openalex.org/W3118815647","doi":"https://doi.org/10.1109/cdc42340.2020.9303830","title":"Taming Convergence for Asynchronous Stochastic Gradient Descent with Unbounded Delay in Non-Convex Learning","display_name":"Taming Convergence for Asynchronous Stochastic Gradient Descent with Unbounded Delay in Non-Convex Learning","publication_year":2020,"publication_date":"2020-12-14","ids":{"openalex":"https://openalex.org/W3118815647","doi":"https://doi.org/10.1109/cdc42340.2020.9303830","mag":"3118815647"},"language":"en","primary_location":{"id":"doi:10.1109/cdc42340.2020.9303830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9303830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","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/A5067715727","display_name":"Xin Zhang","orcid":"https://orcid.org/0000-0003-2901-2593"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Iowa State University, Ames, IA, USA"],"affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625089","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0002-5999-2361"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]},{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["Iowa State University, Ames, IA, USA","The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048337026","display_name":"Zhengyuan Zhu","orcid":"https://orcid.org/0000-0002-2266-0646"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengyuan Zhu","raw_affiliation_strings":["Iowa State University, Ames, IA, USA"],"affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067715727"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76921912,"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":"3580","last_page":"3585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9599999785423279,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8898967504501343},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.8382115364074707},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.687989354133606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6102257370948792},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.6038923859596252},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.527484118938446},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.49983692169189453},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4764944911003113},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.45462560653686523},{"id":"https://openalex.org/keywords/convex-function","display_name":"Convex function","score":0.4459743797779083},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43402808904647827},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3486078977584839},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3045845925807953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20277181267738342},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.08557355403900146},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.08543354272842407},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.04895132780075073}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.8898967504501343},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8382115364074707},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.687989354133606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6102257370948792},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.6038923859596252},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.527484118938446},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.49983692169189453},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4764944911003113},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.45462560653686523},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.4459743797779083},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43402808904647827},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3486078977584839},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3045845925807953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20277181267738342},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.08557355403900146},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08543354272842407},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.04895132780075073},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc42340.2020.9303830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9303830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W778657980","https://openalex.org/W1493782845","https://openalex.org/W1574269637","https://openalex.org/W1779452081","https://openalex.org/W2020098476","https://openalex.org/W2038891887","https://openalex.org/W2049469158","https://openalex.org/W2060393849","https://openalex.org/W2083842231","https://openalex.org/W2138243089","https://openalex.org/W2138601842","https://openalex.org/W2142466236","https://openalex.org/W2161549499","https://openalex.org/W2168231600","https://openalex.org/W2402144811","https://openalex.org/W2569020760","https://openalex.org/W2626580042","https://openalex.org/W2803432032","https://openalex.org/W2953384591","https://openalex.org/W2962834831","https://openalex.org/W2963139509","https://openalex.org/W2963489801","https://openalex.org/W2963903325","https://openalex.org/W2963979747","https://openalex.org/W4297797495","https://openalex.org/W6622473587","https://openalex.org/W6638005537","https://openalex.org/W6660073329","https://openalex.org/W6662929504","https://openalex.org/W6665801690","https://openalex.org/W6680402377","https://openalex.org/W6680894389","https://openalex.org/W6684859321","https://openalex.org/W6713134421","https://openalex.org/W6739554518","https://openalex.org/W6751462397","https://openalex.org/W6766357795"],"related_works":["https://openalex.org/W2895097035","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W3020853991","https://openalex.org/W4362706668","https://openalex.org/W4231621013","https://openalex.org/W3171021120","https://openalex.org/W3008318776"],"abstract_inverted_index":{"Understanding":[0],"the":[1,31,98],"convergence":[2,72,87],"performance":[3],"of":[4,30],"asynchronous":[5],"stochastic":[6],"gradient":[7,39,66,94],"descent":[8],"method":[9],"(Async-SGD)":[10],"has":[11],"received":[12],"increasing":[13,57],"attention":[14],"in":[15,23,97],"recent":[16],"years":[17],"due":[18],"to":[19,36],"their":[20],"foundational":[21],"role":[22],"machine":[24],"learning.":[25],"To":[26],"date,":[27],"however,":[28],"most":[29],"existing":[32],"works":[33],"are":[34],"restricted":[35],"either":[37],"bounded":[38],"delays":[40],"or":[41],"convex":[42],"settings.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"focus":[48],"on":[49],"Async-SGD":[50,75],"and":[51,76],"its":[52],"variant":[53],"Async-SGDI":[54],"(which":[55],"uses":[56],"batch":[58],"size)":[59],"for":[60,74,78,85],"non-convex":[61],"optimization":[62],"problems":[63],"with":[64],"unbounded":[65],"delays.":[67],"We":[68],"prove":[69],"o(1/\u221a":[70],"(k))":[71],"rate":[73],"o(1/k)":[77],"Async-SGDI.":[79],"Also,":[80],"a":[81],"unifying":[82],"sufficient":[83],"assumption":[84],"Async-SGD's":[86],"is":[88],"proposed,":[89],"which":[90],"includes":[91],"two":[92],"major":[93],"delay":[95],"models":[96],"literature":[99],"as":[100],"special":[101],"cases.":[102]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}