{"id":"https://openalex.org/W2585029434","doi":"https://doi.org/10.1109/bigdata.2016.7840590","title":"Predicting statistics of asynchronous SGD parameters for a large-scale distributed deep learning system on GPU supercomputers","display_name":"Predicting statistics of asynchronous SGD parameters for a large-scale distributed deep learning system on GPU supercomputers","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2585029434","doi":"https://doi.org/10.1109/bigdata.2016.7840590","mag":"2585029434"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7840590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","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/A5001297674","display_name":"Yosuke Oyama","orcid":"https://orcid.org/0000-0001-8316-3291"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yosuke Oyama","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000110222","display_name":"Akihiro Nomura","orcid":"https://orcid.org/0000-0002-2417-1723"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiro Nomura","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100862952","display_name":"Ikuro Sato","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ikuro Sato","raw_affiliation_strings":["DENSO IT LABORATORY, INC., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"DENSO IT LABORATORY, INC., Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103225837","display_name":"Hiroki Nishimura","orcid":"https://orcid.org/0009-0001-2832-4934"},"institutions":[{"id":"https://openalex.org/I4210132650","display_name":"Denso (Japan)","ror":"https://ror.org/04hkpfa76","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210132650"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki Nishimura","raw_affiliation_strings":["DENSO CORPORATION, Aichi, Japan"],"affiliations":[{"raw_affiliation_string":"DENSO CORPORATION, Aichi, Japan","institution_ids":["https://openalex.org/I4210132650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047155530","display_name":"Yukimasa Tamatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132650","display_name":"Denso (Japan)","ror":"https://ror.org/04hkpfa76","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210132650"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukimasa Tamatsu","raw_affiliation_strings":["DENSO CORPORATION, Aichi, Japan"],"affiliations":[{"raw_affiliation_string":"DENSO CORPORATION, Aichi, Japan","institution_ids":["https://openalex.org/I4210132650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100634486","display_name":"Satoshi Matsuoka","orcid":"https://orcid.org/0000-0003-1910-8532"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Matsuoka","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001297674"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":2.3381,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.92686324,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/computer-science","display_name":"Computer science","score":0.869825541973114},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.8575628399848938},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.8528554439544678},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6694800853729248},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5933835506439209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4945044219493866},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4115889072418213},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4107971489429474},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40626534819602966},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3731996417045593}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.869825541973114},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8575628399848938},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.8528554439544678},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6694800853729248},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5933835506439209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4945044219493866},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4115889072418213},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4107971489429474},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40626534819602966},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3731996417045593},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2016.7840590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313357","display_name":"Audubon Society of Greater Denver","ror":"https://ror.org/019zjtv03"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1442374986","https://openalex.org/W1563686443","https://openalex.org/W1598866093","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1841592590","https://openalex.org/W2018162709","https://openalex.org/W2087402357","https://openalex.org/W2097117768","https://openalex.org/W2117539524","https://openalex.org/W2133693888","https://openalex.org/W2146502635","https://openalex.org/W2163605009","https://openalex.org/W2168231600","https://openalex.org/W2193413348","https://openalex.org/W2221532093","https://openalex.org/W2293033971","https://openalex.org/W2962911728","https://openalex.org/W2962950660","https://openalex.org/W2963374099","https://openalex.org/W6628377381","https://openalex.org/W6633628269","https://openalex.org/W6635810480","https://openalex.org/W6637373629","https://openalex.org/W6638783484","https://openalex.org/W6679901780","https://openalex.org/W6681435938","https://openalex.org/W6684191040","https://openalex.org/W6684859321","https://openalex.org/W6684953698","https://openalex.org/W6687566353","https://openalex.org/W6688899064","https://openalex.org/W6692488971","https://openalex.org/W6697007688","https://openalex.org/W6780493881"],"related_works":["https://openalex.org/W2168758875","https://openalex.org/W2410733619","https://openalex.org/W4246549241","https://openalex.org/W2963483475","https://openalex.org/W1876383975","https://openalex.org/W2966297898","https://openalex.org/W2955229517","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141"],"abstract_inverted_index":{"Many":[0],"studies":[1],"have":[2],"shown":[3],"that":[4,73,94,151,161],"Deep":[5],"Convolutional":[6],"Neural":[7],"Networks":[8],"(DCNNs)":[9],"exhibit":[10],"great":[11],"accuracies":[12],"given":[13],"large":[14],"training":[15,41,54,69],"datasets":[16],"in":[17,57,132],"image":[18],"recognition":[19,45],"tasks.":[20],"Optimization":[21],"technique":[22],"known":[23],"as":[24,112],"asynchronous":[25,75,100],"mini-batch":[26,80,89,122,166],"Stochastic":[27],"Gradient":[28],"Descent":[29],"(SGD)":[30],"is":[31],"widely":[32],"used":[33],"for":[34],"deep":[35],"learning":[36],"because":[37],"it":[38,48],"gives":[39],"fast":[40],"speed":[42],"and":[43,91,109,115,124,129],"good":[44],"accuracies,":[46],"while":[47],"may":[49],"increases":[50],"generalization":[51],"error":[52,131],"if":[53],"parameters":[55,98],"are":[56,95],"inappropriate":[58],"ranges.":[59],"We":[60],"propose":[61],"a":[62,66,164],"performance":[63,104],"model":[64,83,105,153],"of":[65,88,99,142],"distributed":[67],"DCNN":[68,107],"system":[70],"called":[71],"SPRINT":[72],"uses":[74],"GPU":[76],"processing":[77],"based":[78],"on":[79,135,146],"SGD.":[81],"The":[82],"considers":[84],"the":[85,96,157],"probability":[86],"distribution":[87],"size":[90,123],"gradient":[92],"staleness":[93,125],"core":[97],"SGD":[101],"training.":[102],"Our":[103],"takes":[106],"architecture":[108],"machine":[110,159],"specifications":[111],"input":[113],"parameters,":[114],"predicts":[116],"time":[117],"to":[118,140],"sweep":[119],"entire":[120],"dataset,":[121],"with":[126,138],"5%,":[127],"9%":[128],"19%":[130],"average":[133],"respectively":[134],"several":[136],"supercomputers":[137,149],"up":[139],"thousands":[141],"GPUs.":[143],"Experimental":[144],"results":[145],"two":[147],"different":[148],"show":[150],"our":[152],"can":[154],"steadily":[155],"choose":[156],"fastest":[158],"configuration":[160],"nearly":[162],"meets":[163],"target":[165],"size.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}