{"id":"https://openalex.org/W2556219822","doi":"https://doi.org/10.1109/mlsp.2016.7738878","title":"Stochastic gradient descent with finite samples sizes","display_name":"Stochastic gradient descent with finite samples sizes","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2556219822","doi":"https://doi.org/10.1109/mlsp.2016.7738878","mag":"2556219822"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2016.7738878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2016.7738878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/233532","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100614598","display_name":"Kun Yuan","orcid":"https://orcid.org/0000-0001-8394-8187"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Yuan","raw_affiliation_strings":["Department of Electrical Engineering, University of California, Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005538082","display_name":"Bicheng Ying","orcid":"https://orcid.org/0000-0002-5246-2982"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bicheng Ying","raw_affiliation_strings":["Department of Electrical Engineering, University of California, Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083805703","display_name":"Stefan Vlaski","orcid":"https://orcid.org/0000-0002-0616-3076"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Vlaski","raw_affiliation_strings":["Department of Electrical Engineering, University of California, Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091103447","display_name":"Ali H. Sayed","orcid":"https://orcid.org/0000-0002-5125-5519"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali H. Sayed","raw_affiliation_strings":["Department of Electrical Engineering, University of California, Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":1.5548,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.86665613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9987999796867371,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.7282668948173523},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7108978629112244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6848424673080444},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5567945241928101},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5442386865615845},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5415741205215454},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.43990007042884827},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.4222601056098938},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3984551429748535},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23033073544502258},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1804942786693573},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09351521730422974}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.7282668948173523},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7108978629112244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6848424673080444},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5567945241928101},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5442386865615845},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5415741205215454},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.43990007042884827},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.4222601056098938},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3984551429748535},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23033073544502258},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1804942786693573},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09351521730422974},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mlsp.2016.7738878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2016.7738878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:233532","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/233532","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:233532","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/233532","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W114517082","https://openalex.org/W1568668329","https://openalex.org/W1603765807","https://openalex.org/W1842094663","https://openalex.org/W1992208280","https://openalex.org/W1994389483","https://openalex.org/W1999542175","https://openalex.org/W2012445782","https://openalex.org/W2086161653","https://openalex.org/W2091825929","https://openalex.org/W2101944542","https://openalex.org/W2108948681","https://openalex.org/W2113372738","https://openalex.org/W2113651538","https://openalex.org/W2125993116","https://openalex.org/W2128495863","https://openalex.org/W2156779765","https://openalex.org/W2162287622","https://openalex.org/W2295500362","https://openalex.org/W2560259828","https://openalex.org/W2951488730","https://openalex.org/W4205987271","https://openalex.org/W4238850922","https://openalex.org/W4239240501","https://openalex.org/W6604254268","https://openalex.org/W6638704708","https://openalex.org/W6675995183","https://openalex.org/W6684012599"],"related_works":["https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4231621013","https://openalex.org/W4362706668","https://openalex.org/W3008318776","https://openalex.org/W1977633006","https://openalex.org/W4286899070","https://openalex.org/W1971945429"],"abstract_inverted_index":{"The":[0,99],"minimization":[1],"of":[2,19,37,43,77,89],"empirical":[3,60,87],"risks":[4],"over":[5],"finite":[6],"sample":[7],"sizes":[8],"is":[9,56],"an":[10,128],"important":[11],"problem":[12],"in":[13,24,74,106],"large-scale":[14],"machine":[15],"learning.":[16],"A":[17],"variety":[18],"algorithms":[20],"has":[21],"been":[22],"proposed":[23],"the":[25,29,35,75,107,119],"literature":[26],"to":[27,80,103,133],"alleviate":[28],"computational":[30],"burden":[31],"per":[32],"iteration":[33],"at":[34],"expense":[36],"convergence":[38],"speed":[39],"and":[40,69,96,110,126],"accuracy.":[41],"Many":[42],"these":[44],"approaches":[45],"can":[46],"be":[47],"interpreted":[48],"as":[49],"stochastic":[50,90],"gradient":[51,91,94],"descent":[52],"algorithms,":[53],"where":[54],"data":[55],"sampled":[57],"from":[58,71,122],"particular":[59],"distributions.":[61],"In":[62],"this":[63,67],"work,":[64],"we":[65],"leverage":[66],"interpretation":[68],"draw":[70],"recent":[72],"results":[73],"field":[76],"online":[78],"adaptation":[79],"derive":[81],"new":[82],"tight":[83],"performance":[84,120],"expressions":[85,100],"for":[86],"implementations":[88],"descent,":[92,95],"mini-batch":[93,124],"importance":[97,130],"sampling.":[98],"are":[101,111],"exact":[102],"first":[104],"order":[105],"step-size":[108],"parameter":[109],"tighter":[112],"than":[113],"existing":[114],"bounds.":[115],"We":[116],"further":[117],"quantify":[118],"gained":[121],"employing":[123],"solutions,":[125],"propose":[127],"optimal":[129],"sampling":[131],"algorithm":[132],"optimize":[134],"performance.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}