{"id":"https://openalex.org/W3015618519","doi":"https://doi.org/10.1109/icassp40776.2020.9054292","title":"Balancing Rates and Variance via Adaptive Batch-Sizes in First-Order Stochastic Optimization","display_name":"Balancing Rates and Variance via Adaptive Batch-Sizes in First-Order Stochastic Optimization","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015618519","doi":"https://doi.org/10.1109/icassp40776.2020.9054292","mag":"3015618519"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5088013951","display_name":"Zhan Gao","orcid":"https://orcid.org/0000-0001-7250-7386"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhan Gao","raw_affiliation_strings":["Department of Electrical and Systems Engineering, University of Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Systems Engineering, University of Pennsylvania, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025896653","display_name":"Alec Koppel","orcid":"https://orcid.org/0000-0003-2447-2873"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alec Koppel","raw_affiliation_strings":["Computational and Information Sciences Directorate, U.S. Army Research Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Computational and Information Sciences Directorate, U.S. Army Research Laboratory, USA","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078862959","display_name":"Alejandro Ribeiro","orcid":"https://orcid.org/0000-0003-4230-9906"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alejandro Ribeiro","raw_affiliation_strings":["Department of Electrical and Systems Engineering, University of Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Systems Engineering, University of Pennsylvania, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088013951"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51662642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"25","issue":null,"first_page":"5385","last_page":"5389"},"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/T12676","display_name":"Machine Learning and ELM","score":0.9980999827384949,"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/piecewise","display_name":"Piecewise","score":0.6062703728675842},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.603367805480957},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5653606057167053},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5585671067237854},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.5480031967163086},{"id":"https://openalex.org/keywords/variance-reduction","display_name":"Variance reduction","score":0.5271950364112854},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.518122136592865},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.5162229537963867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5134781002998352},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5099104642868042},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5015628337860107},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4593406617641449},{"id":"https://openalex.org/keywords/approximation-error","display_name":"Approximation error","score":0.4431857168674469},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38808637857437134},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.38613438606262207},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.15832945704460144},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12375679612159729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08138471841812134}],"concepts":[{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.6062703728675842},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.603367805480957},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5653606057167053},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5585671067237854},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5480031967163086},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.5271950364112854},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.518122136592865},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.5162229537963867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5134781002998352},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5099104642868042},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5015628337860107},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4593406617641449},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.4431857168674469},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38808637857437134},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.38613438606262207},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.15832945704460144},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12375679612159729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08138471841812134},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","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/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":30,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W1507126399","https://openalex.org/W1522301498","https://openalex.org/W1554944419","https://openalex.org/W1568668329","https://openalex.org/W1774344329","https://openalex.org/W1992208280","https://openalex.org/W1994616650","https://openalex.org/W2020909452","https://openalex.org/W2034996255","https://openalex.org/W2038084402","https://openalex.org/W2060471940","https://openalex.org/W2061570747","https://openalex.org/W2072566913","https://openalex.org/W2091825929","https://openalex.org/W2103628399","https://openalex.org/W2108948681","https://openalex.org/W2124541940","https://openalex.org/W2171033594","https://openalex.org/W2661056902","https://openalex.org/W2951488730","https://openalex.org/W2962930217","https://openalex.org/W2964067433","https://openalex.org/W2964121744","https://openalex.org/W3125937743","https://openalex.org/W3141595720","https://openalex.org/W6631190155","https://openalex.org/W6668562388","https://openalex.org/W6675995183","https://openalex.org/W6739947481"],"related_works":["https://openalex.org/W2107438106","https://openalex.org/W4286899070","https://openalex.org/W4323366756","https://openalex.org/W3207830353","https://openalex.org/W4285259204","https://openalex.org/W3109737792","https://openalex.org/W3109198354","https://openalex.org/W937081240","https://openalex.org/W2760303966","https://openalex.org/W4401866412"],"abstract_inverted_index":{"Stochastic":[0],"gradient":[1,131],"descent":[2],"is":[3,34,82,99,104,121,140],"a":[4,71,86,95,156],"canonical":[5],"tool":[6],"for":[7,36],"addressing":[8],"stochastic":[9,130],"optimization":[10],"problems,":[11],"and":[12,20,64],"forms":[13],"the":[14,29,41,62,67,80,91,102,110,125,135,169],"bedrock":[15],"of":[16,129,172],"modern":[17],"machine":[18],"learning":[19],"statistics.":[21],"In":[22],"this":[23],"work,":[24],"we":[25,69,154],"seek":[26],"to":[27,53,73,76,84,123,160],"balance":[28],"fact":[30,42],"that":[31,43,107],"attenuating":[32],"step-sizes":[33,46],"required":[35],"exact":[37,126],"asymptotic":[38,127],"convergence":[39,128],"with":[40],"larger":[44],"constant":[45],"learn":[47],"faster":[48],"in":[49,149],"finite":[50],"time":[51],"up":[52],"an":[54,146],"error.":[55],"To":[56],"do":[57],"so,":[58],"rather":[59],"than":[60],"fixing":[61],"mini-batch":[63],"step-size":[65,103],"at":[66],"outset,":[68],"propose":[70],"strategy":[72],"allow":[74],"parameters":[75],"evolve":[77],"adaptively.":[78],"Specifically,":[79],"batch-size":[81],"set":[83],"be":[85],"piecewise-constant":[87],"increasing":[88],"sequence":[89],"where":[90],"increase":[92],"occurs":[93],"when":[94],"suitable":[96],"error":[97,137],"criterion":[98],"satisfied.":[100],"Moreover,":[101],"selected":[105],"as":[106,143,145],"which":[108,167],"yields":[109],"fastest":[111],"convergence.":[112],"The":[113],"overall":[114,147],"algorithm,":[115],"two":[116],"scale":[117],"adaptive":[118],"(TSA)":[119],"scheme,":[120],"shown":[122],"inherit":[124],"method.":[132],"More":[133],"importantly,":[134],"optimal":[136],"decreasing":[138],"rate":[139],"achieved":[141],"theoretically,":[142],"well":[144],"reduction":[148],"sample":[150],"computational":[151],"cost.":[152],"Experimentally,":[153],"observe":[155],"favorable":[157],"tradeoff":[158],"relative":[159],"standard":[161],"SGD":[162],"schemes":[163],"absorbing":[164],"their":[165],"advantages,":[166],"illustrates":[168],"significant":[170],"performance":[171],"proposed":[173],"TSA":[174],"scheme.":[175]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}