{"id":"https://openalex.org/W2744599870","doi":"https://doi.org/10.24963/ijcai.2018/447","title":"On the Convergence Properties of a K-step Averaging Stochastic Gradient Descent Algorithm for Nonconvex Optimization","display_name":"On the Convergence Properties of a K-step Averaging Stochastic Gradient Descent Algorithm for Nonconvex Optimization","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2744599870","doi":"https://doi.org/10.24963/ijcai.2018/447","mag":"2744599870"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/447","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/447","pdf_url":"https://www.ijcai.org/proceedings/2018/0447.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0447.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Fan Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan Zhou","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":null,"display_name":"Guojing Cong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guojing Cong","raw_affiliation_strings":["IBM Thomas J. Watson Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0535,"has_fulltext":false,"cited_by_count":86,"citation_normalized_percentile":{"value":0.93863051,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3219","last_page":"3227"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9983999729156494,"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":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.8342999815940857},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7735000252723694},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7138000130653381},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5960000157356262},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.48429998755455017},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45570001006126404},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.40459999442100525}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8342999815940857},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7735000252723694},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7138000130653381},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5960000157356262},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.501800000667572},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.48429998755455017},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4796999990940094},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45570001006126404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4424000084400177},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42250001430511475},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C95763700","wikidata":"https://www.wikidata.org/wiki/Q578985","display_name":"Convergence of random variables","level":3,"score":0.3248000144958496},{"id":"https://openalex.org/C116149140","wikidata":"https://www.wikidata.org/wiki/Q2070951","display_name":"Descent direction","level":4,"score":0.3165999948978424},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.314300000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2018/447","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/447","pdf_url":"https://www.ijcai.org/proceedings/2018/0447.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1708.01012","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.01012","pdf_url":"https://arxiv.org/pdf/1708.01012","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":"doi:10.24963/ijcai.2018/447","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/447","pdf_url":"https://www.ijcai.org/proceedings/2018/0447.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7948674678","display_name":"CIF: Small: Statistical Inference via Convex Optimization","funder_award_id":"1523768","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8046157894","display_name":"Asymptotics and concentration in spectral estimation for large matrices","funder_award_id":"1509739","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2744599870.pdf","grobid_xml":"https://content.openalex.org/works/W2744599870.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,23,45,71],"adopt":[1],"and":[2,53,101,117,121],"analyze":[3],"a":[4,106],"synchronous":[5,43],"K-step":[6,49],"averaging":[7],"stochastic":[8,61,85],"gradient":[9,62,86],"descent":[10,63,87],"algorithm":[11],"which":[12,64],"we":[13],"call":[14],"K-AVG":[15,29,36,68,75,92,111],"for":[16,30,124],"solving":[17],"large":[18],"scale":[19],"machine":[20],"learning":[21],"problems.":[22],"establish":[24],"the":[25,48,79,127],"convergence":[26,123],"results":[27],"of":[28,35,42,81,91,108],"nonconvex":[31],"objectives.":[32],"Our":[33],"analysis":[34],"applies":[37],"to":[38,55,67],"many":[39],"existing":[40],"variants":[41],"SGD.":[44],"explain":[46],"why":[47],"delay":[50],"is":[51,65,95,112],"necessary":[52],"leads":[54],"better":[56,77,119],"performance":[57],"than":[58,83,114],"traditional":[59],"parallel":[60],"equivalent":[66],"with":[69,78,126],"$K=1$.":[70],"also":[72],"show":[73],"that":[74,96],"scales":[76],"number":[80],"learners":[82],"asynchronous":[84],"(ASGD).":[88],"Another":[89],"advantage":[90],"over":[93],"ASGD":[94,115],"it":[97],"allows":[98],"larger":[99],"stepsizes":[100],"facilitates":[102],"faster":[103,113,122],"convergence.":[104],"On":[105],"cluster":[107],"$128$":[109],"GPUs,":[110],"implementations":[116],"achieves":[118],"accuracies":[120],"training":[125],"CIFAR-10":[128],"dataset.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2017-08-17T00:00:00"}