{"id":"https://openalex.org/W2783547213","doi":"https://doi.org/10.1109/cdc.2017.8264077","title":"Mini-batch gradient descent: Faster convergence under data sparsity","display_name":"Mini-batch gradient descent: Faster convergence under data sparsity","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2783547213","doi":"https://doi.org/10.1109/cdc.2017.8264077","mag":"2783547213"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2017.8264077","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2017.8264077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 56th Annual 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/A5027182415","display_name":"Sarit Khirirat","orcid":"https://orcid.org/0000-0003-4473-2011"},"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":"Sarit Khirirat","raw_affiliation_strings":["Department of Automatic Control, Royal Institute of Technology (KTH), Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automatic Control, Royal Institute of Technology (KTH), Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038418293","display_name":"Hamid Reza Feyzmahdavian","orcid":"https://orcid.org/0000-0003-1149-4715"},"institutions":[{"id":"https://openalex.org/I4210086503","display_name":"ABB (Sweden)","ror":"https://ror.org/0033n4009","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210086503","https://openalex.org/I885143765"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Hamid Reza Feyzmahdavian","raw_affiliation_strings":["ABB Corporate Research Center, Vaster\u00e5s, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ABB Corporate Research Center, Vaster\u00e5s, Sweden","institution_ids":["https://openalex.org/I4210086503"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024256519","display_name":"Mikael Johansson","orcid":"https://orcid.org/0000-0002-2237-2580"},"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":"Mikael Johansson","raw_affiliation_strings":["Department of Automatic Control, Royal Institute of Technology (KTH), Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automatic Control, Royal Institute of Technology (KTH), Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4458,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":{"value":0.87379517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2880","last_page":"2887"},"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9997000098228455,"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/T12676","display_name":"Machine Learning and ELM","score":0.9991000294685364,"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":0.8642593622207642},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.7163650989532471},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7138482332229614},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6803240776062012},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.6140995621681213},{"id":"https://openalex.org/keywords/descent","display_name":"Descent (aeronautics)","score":0.5908033847808838},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5826789140701294},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.46152463555336},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43254342675209045},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4219667315483093},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4113016128540039},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32153114676475525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2809235453605652},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24937230348587036},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.077475905418396},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05699095129966736}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8642593622207642},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.7163650989532471},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7138482332229614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6803240776062012},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.6140995621681213},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.5908033847808838},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5826789140701294},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.46152463555336},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43254342675209045},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4219667315483093},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4113016128540039},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32153114676475525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2809235453605652},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24937230348587036},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.077475905418396},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05699095129966736},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2017.8264077","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2017.8264077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 56th Annual Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W778657980","https://openalex.org/W1536816303","https://openalex.org/W1576520375","https://openalex.org/W1955857676","https://openalex.org/W1974680426","https://openalex.org/W1992208280","https://openalex.org/W2047152541","https://openalex.org/W2080335539","https://openalex.org/W2109943925","https://openalex.org/W2113651538","https://openalex.org/W2130062883","https://openalex.org/W2134130436","https://openalex.org/W2138243089","https://openalex.org/W2153635508","https://openalex.org/W2162287622","https://openalex.org/W2166706236","https://openalex.org/W2168914046","https://openalex.org/W2409036552","https://openalex.org/W2619493178","https://openalex.org/W2949585412","https://openalex.org/W2962952793","https://openalex.org/W2963903325","https://openalex.org/W3123607434","https://openalex.org/W4299028886","https://openalex.org/W4299824912","https://openalex.org/W6622473587","https://openalex.org/W6632084258","https://openalex.org/W6634442568","https://openalex.org/W6679314259","https://openalex.org/W6680008295","https://openalex.org/W6684012599","https://openalex.org/W6684249991","https://openalex.org/W6685044387","https://openalex.org/W6764309476"],"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/W2015288657","https://openalex.org/W3171021120"],"abstract_inverted_index":{"The":[0,95],"practical":[1],"performance":[2,100],"of":[3,65,72,101],"stochastic":[4],"gradient":[5,74,110],"descent":[6,111],"on":[7,88],"large-scale":[8],"machine":[9,86],"learning":[10],"tasks":[11],"is":[12,27,50],"often":[13],"much":[14],"better":[15],"than":[16],"what":[17],"current":[18],"theoretical":[19,77],"tools":[20],"can":[21],"guarantee.":[22],"This":[23],"indicates":[24],"that":[25,34,47],"there":[26],"an":[28],"inherent":[29],"structure":[30],"in":[31],"these":[32],"problems":[33,87],"could":[35],"be":[36],"exploited":[37],"to":[38,106],"strengthen":[39],"the":[40,63,69,107],"analysis.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"argue":[46],"data":[48,60,93],"sparsity":[49,61],"such":[51],"a":[52],"property.":[53],"We":[54],"derive":[55],"explicit":[56],"expressions":[57],"for":[58],"how":[59],"affects":[62],"range":[64],"admissible":[66],"step-sizes":[67],"and":[68,91],"convergence":[70],"factors":[71],"minibatch":[73],"descent.":[75],"Our":[76],"results":[78,97],"are":[79],"validated":[80],"by":[81],"solving":[82],"least-squares":[83],"support":[84],"vector":[85],"both":[89],"synthetic":[90],"real-life":[92],"sets.":[94],"experimental":[96],"demonstrate":[98],"improved":[99],"our":[102],"update":[103],"rules":[104],"compared":[105],"traditional":[108],"mini-batch":[109],"algorithm.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}