{"id":"https://openalex.org/W2985438839","doi":"https://doi.org/10.1109/dls49591.2019.00013","title":"DC-S3GD: Delay-Compensated Stale-Synchronous SGD for Large-Scale Decentralized Neural Network Training","display_name":"DC-S3GD: Delay-Compensated Stale-Synchronous SGD for Large-Scale Decentralized Neural Network Training","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2985438839","doi":"https://doi.org/10.1109/dls49591.2019.00013","mag":"2985438839"},"language":"en","primary_location":{"id":"doi:10.1109/dls49591.2019.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dls49591.2019.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM Third Workshop on Deep Learning on Supercomputers (DLS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.02516","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076174102","display_name":"Alessandro Rigazzi","orcid":"https://orcid.org/0000-0003-2132-7726"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alessandro Rigazzi","raw_affiliation_strings":["Cray Inc, Basel, Switzerland","Cray Inc, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cray Inc, Basel, Switzerland","institution_ids":[]},{"raw_affiliation_string":"Cray Inc, Switzerland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5076174102"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13997402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 1512 1274","issue":null,"first_page":"62","last_page":"68"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9990000128746033,"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/asynchronous-communication","display_name":"Asynchronous communication","score":0.8843852281570435},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8002896308898926},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6548557281494141},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6259446144104004},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5756625533103943},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5325621366500854},{"id":"https://openalex.org/keywords/de-facto","display_name":"De facto","score":0.528455913066864},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5245746970176697},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4956728219985962},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.42418789863586426},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4123801589012146},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34914907813072205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31299862265586853},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3069070875644684},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.24895673990249634}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.8843852281570435},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8002896308898926},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6548557281494141},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6259446144104004},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5756625533103943},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5325621366500854},{"id":"https://openalex.org/C2992317946","wikidata":"https://www.wikidata.org/wiki/Q712144","display_name":"De facto","level":2,"score":0.528455913066864},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5245746970176697},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4956728219985962},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.42418789863586426},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4123801589012146},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34914907813072205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31299862265586853},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3069070875644684},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.24895673990249634},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/dls49591.2019.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dls49591.2019.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM Third Workshop on Deep Learning on Supercomputers (DLS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.02516","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.02516","pdf_url":"https://arxiv.org/pdf/1911.02516","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},{"id":"mag:2985438839","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1911.02516","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.1911.02516","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.02516","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.02516","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.02516","pdf_url":"https://arxiv.org/pdf/1911.02516","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2985438839.pdf","grobid_xml":"https://content.openalex.org/works/W2985438839.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1598866093","https://openalex.org/W1980287119","https://openalex.org/W2186615578","https://openalex.org/W2523925604","https://openalex.org/W2622263826","https://openalex.org/W2647555508","https://openalex.org/W2749988060","https://openalex.org/W2755682530","https://openalex.org/W2757910899","https://openalex.org/W2769582697","https://openalex.org/W2788193959","https://openalex.org/W2884711234","https://openalex.org/W2903697572","https://openalex.org/W2918712153","https://openalex.org/W2949227242","https://openalex.org/W2962933129","https://openalex.org/W2963173418","https://openalex.org/W2963964896","https://openalex.org/W6686509673","https://openalex.org/W6728005305","https://openalex.org/W6740196363","https://openalex.org/W6743289643","https://openalex.org/W6743955621","https://openalex.org/W6744513255","https://openalex.org/W6745558287","https://openalex.org/W6746408925","https://openalex.org/W6747381837","https://openalex.org/W6749107692","https://openalex.org/W6753209298","https://openalex.org/W6757053730","https://openalex.org/W6760426467","https://openalex.org/W6763140458"],"related_works":["https://openalex.org/W2897662618","https://openalex.org/W1982091794","https://openalex.org/W1629434287","https://openalex.org/W2391704877","https://openalex.org/W2161768744","https://openalex.org/W2353284380","https://openalex.org/W1607950937","https://openalex.org/W2105006514","https://openalex.org/W2111652403","https://openalex.org/W2130424900","https://openalex.org/W2133882365","https://openalex.org/W17918833","https://openalex.org/W2388987802","https://openalex.org/W2058985907","https://openalex.org/W2348821729","https://openalex.org/W2378884150","https://openalex.org/W2435110254","https://openalex.org/W2152588031","https://openalex.org/W2099868257","https://openalex.org/W2062201753"],"abstract_inverted_index":{"Data":[0],"parallelism":[1],"has":[2],"become":[3],"the":[4,31,46,59,67,73],"de":[5],"facto":[6],"standard":[7],"for":[8,45],"training":[9,79],"Deep":[10],"Neural":[11,81],"Network":[12,82],"on":[13],"multiple":[14],"processing":[15],"units.":[16],"In":[17,40],"this":[18],"work":[19],"we":[20,43],"propose":[21],"DC-S3GD,":[22],"a":[23,63],"decentralized":[24],"(without":[25],"Parameter":[26],"Server)":[27],"stale-synchronous":[28],"version":[29],"of":[30,48,66,75],"Delay-Compensated":[32],"Asynchronous":[33],"Stochastic":[34],"Gradient":[35],"Descent":[36],"(DC-":[37],"ASGD)":[38],"algorithm.":[39],"our":[41,76],"approach,":[42],"allow":[44],"overlap":[47],"computation":[49],"and":[50,57,86],"communication,":[51],"by":[52,78],"averaging":[53],"in":[54],"parameter":[55],"space":[56],"compensating":[58],"inherent":[60],"error":[61],"with":[62,83],"first-order":[64],"correction":[65],"locally":[68],"computed":[69],"gradients.":[70],"We":[71],"prove":[72],"effectiveness":[74],"approach":[77],"Convolutional":[80],"large":[84],"batches":[85],"achieving":[87],"state-of-":[88],"the-art":[89],"results.":[90]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}