{"id":"https://openalex.org/W2744829609","doi":"https://doi.org/10.1145/3097983.3098147","title":"Small Batch or Large Batch?","display_name":"Small Batch or Large Batch?","publication_year":2017,"publication_date":"2017-08-04","ids":{"openalex":"https://openalex.org/W2744829609","doi":"https://doi.org/10.1145/3097983.3098147","mag":"2744829609"},"language":"en","primary_location":{"id":"doi:10.1145/3097983.3098147","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3097983.3098147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5049036241","display_name":"Peifeng Yin","orcid":"https://orcid.org/0000-0002-0109-7903"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peifeng Yin","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046387024","display_name":"Ping Luo","orcid":"https://orcid.org/0000-0003-2512-0415"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Luo","raw_affiliation_strings":["Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074644024","display_name":"Taiga Nakamura","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taiga Nakamura","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1275","last_page":"1284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9958999752998352,"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":0.9955000281333923,"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":0.7487385272979736},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7170796394348145},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5350882411003113},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.508683979511261},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4977903366088867},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4956151247024536},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.4903886318206787},{"id":"https://openalex.org/keywords/batch-processing","display_name":"Batch processing","score":0.4677572250366211},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.44393351674079895},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.43336522579193115},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4220935106277466},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.372048556804657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26799386739730835},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22990566492080688},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1335086226463318}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.7487385272979736},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7170796394348145},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5350882411003113},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.508683979511261},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4977903366088867},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4956151247024536},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.4903886318206787},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.4677572250366211},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.44393351674079895},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.43336522579193115},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4220935106277466},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.372048556804657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26799386739730835},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22990566492080688},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1335086226463318},{"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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3097983.3098147","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3097983.3098147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6299999952316284}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W114517082","https://openalex.org/W1554447113","https://openalex.org/W1786620475","https://openalex.org/W1939652453","https://openalex.org/W1980287119","https://openalex.org/W1992841740","https://openalex.org/W2045079045","https://openalex.org/W2047152541","https://openalex.org/W2068484625","https://openalex.org/W2072566913","https://openalex.org/W2078945459","https://openalex.org/W2083842231","https://openalex.org/W2085988980","https://openalex.org/W2086161653","https://openalex.org/W2096544401","https://openalex.org/W2105875671","https://openalex.org/W2106728335","https://openalex.org/W2107438106","https://openalex.org/W2130486630","https://openalex.org/W2132737349","https://openalex.org/W2133941677","https://openalex.org/W2138243089","https://openalex.org/W2138996412","https://openalex.org/W2146502635","https://openalex.org/W2164278908","https://openalex.org/W2166706236","https://openalex.org/W2168231600","https://openalex.org/W2173213060","https://openalex.org/W2188978913","https://openalex.org/W2189465200","https://openalex.org/W2244987555","https://openalex.org/W2271840356","https://openalex.org/W2559655401","https://openalex.org/W2596585349","https://openalex.org/W2604272474","https://openalex.org/W2951781666","https://openalex.org/W2951833684","https://openalex.org/W2952594493","https://openalex.org/W2969945254","https://openalex.org/W2998508934","https://openalex.org/W3120740533","https://openalex.org/W4292363360","https://openalex.org/W6684249991"],"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/W2041416246","https://openalex.org/W3020853991","https://openalex.org/W2801374625"],"abstract_inverted_index":{"Efficiency":[0],"of":[1,39,51,63,104,115,132,142,170],"large-scale":[2],"learning":[3,75,98],"is":[4,136],"a":[5,60,70,82,93,119,129],"hot":[6],"topic":[7],"in":[8,59,73],"both":[9],"academic":[10],"and":[11,19,107],"industry.":[12],"The":[13],"stochastic":[14,84],"gradient":[15,41,85],"descent":[16,86],"(SGD)":[17],"algorithm,":[18,88],"its":[20],"extension":[21,106],"mini-batch":[22],"SGD,":[23],"allow":[24],"the":[25,32,37,44,49,67,102,113,140,159,162,167],"model":[26,178],"to":[27,43,138],"be":[28],"updated":[29],"without":[30],"scanning":[31],"whole":[33],"data":[34,151],"set.":[35],"However,":[36],"use":[38],"approximate":[40],"leads":[42],"uncertainty":[45,56],"issue,":[46],"slowing":[47],"down":[48],"decreasing":[50],"objective":[52,116],"function.":[53],"Furthermore,":[54],"such":[55],"may":[57],"result":[58],"high":[61],"frequency":[62],"meaningless":[64],"update":[65],"on":[66,101,148],"model,":[68],"causing":[69],"communication":[71],"issue":[72],"parallel":[74],"environment.":[76],"In":[77,126],"this":[78,127],"work,":[79],"we":[80,153],"develop":[81],"batch-adaptive":[83],"(BA-SGD)":[87],"which":[89],"can":[90],"dynamically":[91],"choose":[92],"proper":[94],"batch":[95,134,160],"size":[96,135],"as":[97,118],"proceeds.":[99],"Particularly":[100],"basis":[103],"Taylor":[105],"central":[108],"limit":[109],"theorem,":[110],"it":[111],"models":[112],"decrease":[114],"value":[117],"Gaussian":[120],"random":[121],"walk":[122],"game":[123],"with":[124],"rebound.":[125],"game,":[128],"heuristic":[130],"strategy":[131],"determining":[133],"adopted":[137],"maximize":[139],"utility":[141],"each":[143],"incremental":[144],"sampling.":[145],"By":[146],"evaluation":[147],"multiple":[149],"real":[150],"sets,":[152],"demonstrate":[154],"that":[155],"by":[156],"smartly":[157],"choosing":[158],"size,":[161],"BA-SGD":[163],"not":[164],"only":[165],"conserves":[166],"fast":[168],"convergence":[169],"SGD":[171],"algorithm":[172],"but":[173],"also":[174],"avoids":[175],"too":[176],"frequent":[177],"updates.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}