{"id":"https://openalex.org/W3037647089","doi":"https://doi.org/10.1109/mascots50786.2020.9285954","title":"Effective Elastic Scaling of Deep Learning Workloads","display_name":"Effective Elastic Scaling of Deep Learning Workloads","publication_year":2020,"publication_date":"2020-11-17","ids":{"openalex":"https://openalex.org/W3037647089","doi":"https://doi.org/10.1109/mascots50786.2020.9285954","mag":"3037647089"},"language":"en","primary_location":{"id":"doi:10.1109/mascots50786.2020.9285954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mascots50786.2020.9285954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.13878","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044459787","display_name":"Vaibhav Saxena","orcid":"https://orcid.org/0000-0002-7681-5033"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vaibhav Saxena","raw_affiliation_strings":["IBM Research, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086724836","display_name":"K. R. Jayaram","orcid":"https://orcid.org/0000-0001-5382-276X"},"institutions":[{"id":"https://openalex.org/I4210156936","display_name":"IBM Research - Austin","ror":"https://ror.org/05gjbbg60","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210156936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. R. Jayaram","raw_affiliation_strings":["IBM Research, USA","IBM Research (USA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]},{"raw_affiliation_string":"IBM Research (USA)","institution_ids":["https://openalex.org/I4210156936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113524886","display_name":"Saurav Basu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162141","display_name":"Microsoft (India)","ror":"https://ror.org/04ww0w091","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210162141"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Saurav Basu","raw_affiliation_strings":["Microsoft, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, India","institution_ids":["https://openalex.org/I4210162141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033885850","display_name":"Yogish Sabharwal","orcid":"https://orcid.org/0009-0002-5053-2059"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yogish Sabharwal","raw_affiliation_strings":["IBM Research, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101423308","display_name":"Ashish Verma","orcid":"https://orcid.org/0009-0007-3427-3196"},"institutions":[{"id":"https://openalex.org/I4210156936","display_name":"IBM Research - Austin","ror":"https://ror.org/05gjbbg60","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210156936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashish Verma","raw_affiliation_strings":["IBM Research, USA","IBM Research (USA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]},{"raw_affiliation_string":"IBM Research (USA)","institution_ids":["https://openalex.org/I4210156936"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2708,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63713767,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/exploit","display_name":"Exploit","score":0.7975215315818787},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7492289543151855},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6546916961669922},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5559852719306946},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.5134447813034058},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5022008419036865},{"id":"https://openalex.org/keywords/approx","display_name":"Approx","score":0.4786437749862671},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43198758363723755},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4244958758354187},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.4236985743045807},{"id":"https://openalex.org/keywords/premise","display_name":"Premise","score":0.42294007539749146},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.4219997823238373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4121597111225128},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.356201708316803},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1110968291759491},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09336850047111511},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09288308024406433}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7975215315818787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7492289543151855},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6546916961669922},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5559852719306946},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.5134447813034058},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5022008419036865},{"id":"https://openalex.org/C2777894999","wikidata":"https://www.wikidata.org/wiki/Q4781758","display_name":"Approx","level":2,"score":0.4786437749862671},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43198758363723755},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4244958758354187},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.4236985743045807},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.42294007539749146},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.4219997823238373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4121597111225128},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.356201708316803},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1110968291759491},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09336850047111511},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09288308024406433},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/mascots50786.2020.9285954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mascots50786.2020.9285954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2006.13878","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.13878","pdf_url":"https://arxiv.org/pdf/2006.13878","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},{"id":"mag:3037647089","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2006.13878","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2006.13878","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.13878","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.13878","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.13878","pdf_url":"https://arxiv.org/pdf/2006.13878","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":[{"display_name":"Decent work and economic growth","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3037647089.pdf"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W167093911","https://openalex.org/W1575092331","https://openalex.org/W1743501494","https://openalex.org/W2075233755","https://openalex.org/W2114869027","https://openalex.org/W2145457647","https://openalex.org/W2155893237","https://openalex.org/W2163961697","https://openalex.org/W2436219157","https://openalex.org/W2511250460","https://openalex.org/W2553605439","https://openalex.org/W2591836544","https://openalex.org/W2606207877","https://openalex.org/W2622263826","https://openalex.org/W2623919293","https://openalex.org/W2757910899","https://openalex.org/W2773689216","https://openalex.org/W2782514582","https://openalex.org/W2798134103","https://openalex.org/W2807996351","https://openalex.org/W2885836230","https://openalex.org/W2891048762","https://openalex.org/W2892643113","https://openalex.org/W2899071864","https://openalex.org/W2919594608","https://openalex.org/W2962684017","https://openalex.org/W2962725887","https://openalex.org/W2962835968","https://openalex.org/W2963281229","https://openalex.org/W2963403751","https://openalex.org/W2963433607","https://openalex.org/W2963456262","https://openalex.org/W2963702144","https://openalex.org/W2963959597","https://openalex.org/W2972392561","https://openalex.org/W3102643349","https://openalex.org/W6637863832","https://openalex.org/W6732127223","https://openalex.org/W6739622702","https://openalex.org/W6745410505","https://openalex.org/W6756009870","https://openalex.org/W6758283263"],"related_works":["https://openalex.org/W3113635268","https://openalex.org/W2899071864","https://openalex.org/W3092490437","https://openalex.org/W3012536640","https://openalex.org/W3176889093","https://openalex.org/W143203712","https://openalex.org/W3082266397","https://openalex.org/W2105096092","https://openalex.org/W3212545986","https://openalex.org/W3000872410","https://openalex.org/W2172014267","https://openalex.org/W3047439613","https://openalex.org/W2309679942","https://openalex.org/W2759085228","https://openalex.org/W2565387986","https://openalex.org/W3198816945","https://openalex.org/W3022548332","https://openalex.org/W2413498683","https://openalex.org/W2792596678","https://openalex.org/W2891585392"],"abstract_inverted_index":{"We":[0,34,61,87,129],"examine":[1],"the":[2,42,119,154,162],"elastic":[3,134],"scaling":[4,80,135],"of":[5,53,125,156],"Deep":[6],"Learning":[7],"(DL)":[8],"jobs":[9,46,76,103,143],"and":[10,40,109,122],"propose":[11],"a":[12,51,68,89,147],"novel":[13],"resource":[14],"allocation":[15,72],"strategy":[16],"for":[17],"DL":[18,38,45,75,127],"training":[19],"jobs,":[20],"resulting":[21],"in":[22,99,113],"improved":[23],"job":[24],"run":[25,49],"time":[26],"performance":[27],"as":[28,30,141,144],"well":[29],"increased":[31],"cluster":[32],"utilization.":[33],"begin":[35],"by":[36],"analyzing":[37],"workloads":[39],"exploit":[41],"fact":[43],"that":[44,66,104,132,151],"can":[47,105,137],"be":[48,106],"with":[50,165],"range":[52],"batch":[54,70,123,163],"sizes":[55,124],"without":[56],"affecting":[57],"their":[58,79],"final":[59],"accuracy.":[60],"formulate":[62],"an":[63,114],"optimization":[64],"problem":[65,98],"explores":[67],"dynamic":[69,91],"size":[71],"to":[73,95,101,116,140,146,170],"individual":[74,126],"based":[77,93],"on":[78,84],"efficiency,":[81],"when":[82],"running":[83],"multiple":[85],"nodes.":[86],"design":[88],"fast":[90],"programming":[92],"optimizer":[94,112],"solve":[96],"this":[97,111],"real-time":[100],"determine":[102],"scaled":[107],"up/down,":[108],"use":[110],"autoscaler":[115],"dynamically":[117],"change":[118,161],"allocated":[120],"resources":[121],"jobs.":[128],"demonstrate":[130],"empirically":[131],"our":[133],"algorithm":[136,150],"complete":[138],"up":[139,169],"many":[142],"compared":[145],"strong":[148],"baseline":[149],"also":[152],"scales":[153],"number":[155],"GPUs":[157],"but":[158],"does":[159],"not":[160],"size,":[164],"average":[166],"completion":[167],"times":[168],"faster.":[171]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}