{"id":"https://openalex.org/W2523925604","doi":"https://doi.org/10.48550/arxiv.1609.08326","title":"Asynchronous Stochastic Gradient Descent with Delay Compensation","display_name":"Asynchronous Stochastic Gradient Descent with Delay Compensation","publication_year":2016,"publication_date":"2016-09-27","ids":{"openalex":"https://openalex.org/W2523925604","doi":"https://doi.org/10.48550/arxiv.1609.08326","mag":"2523925604"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1609.08326","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1609.08326","pdf_url":"https://arxiv.org/pdf/1609.08326","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1609.08326","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051093347","display_name":"Shuxin Zheng","orcid":"https://orcid.org/0000-0001-7828-5374","observed_orcids":["https://orcid.org/0000-0001-7828-5374"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Shuxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101704281","display_name":"Qi Meng","orcid":"https://orcid.org/0000-0001-7082-6666","observed_orcids":["https://orcid.org/0000-0001-7082-6666"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074676968","display_name":"Taifeng Wang","orcid":"https://orcid.org/0009-0007-1116-0228","observed_orcids":["https://orcid.org/0009-0007-1116-0228"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Taifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059286427","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0003-3316-0417","observed_orcids":["https://orcid.org/0000-0003-3316-0417"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064573190","display_name":"Nenghai Yu","orcid":"https://orcid.org/0000-0003-4417-9316","observed_orcids":["https://orcid.org/0000-0003-4417-9316"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Nenghai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078600050","display_name":"Zhi-Ming Ma","orcid":"https://orcid.org/0000-0001-6453-4368","observed_orcids":["https://orcid.org/0000-0001-6453-4368"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Zhi-Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5115592065","display_name":"Tie\u2010Yan Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Tie-Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":251,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T12535","display_name":"Machine Learning and Data Classification","score":9.999999747378752e-05,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":9.999999747378752e-05,"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/asynchronous-stochastic-gradient-descent","display_name":"asynchronous stochastic gradient descent","score":0.9959999918937683},{"id":"https://openalex.org/keywords/time-delay-compensation","display_name":"time delay compensation","score":0.9559999704360962},{"id":"https://openalex.org/keywords/distributed-deep-learning","display_name":"distributed deep learning","score":0.984000027179718},{"id":"https://openalex.org/keywords/hessian-approximation","display_name":"Hessian approximation","score":0.7400000095367432},{"id":"https://openalex.org/keywords/taylor-expansion","display_name":"Taylor series expansion","score":0.8130000233650208},{"id":"https://openalex.org/keywords/large-scale-neural-network-training","display_name":"large-scale neural network training","score":0.6200000047683716}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.8612279891967773},{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.7853894233703613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7606992721557617},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.737758457660675},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6507971882820129},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4737597107887268},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4731284976005554},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44491520524024963},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4300963878631592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40160393714904785},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3973648250102997},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13524487614631653},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.10032060742378235},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08010044693946838},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1609.08326","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1609.08326","pdf_url":"https://arxiv.org/pdf/1609.08326","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,"listed_in":[],"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:2523925604","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1609.08326v1","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,"listed_in":[],"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.1609.08326","doi":"https://doi.org/10.48550/arxiv.1609.08326","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1609.08326","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1609.08326","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1609.08326","pdf_url":"https://arxiv.org/pdf/1609.08326","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2523925604.pdf","grobid_xml":"https://content.openalex.org/works/W2523925604.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W19621276","https://openalex.org/W196761320","https://openalex.org/W778657980","https://openalex.org/W1845277745","https://openalex.org/W1899249567","https://openalex.org/W1955857676","https://openalex.org/W1988115241","https://openalex.org/W2047692660","https://openalex.org/W2117539524","https://openalex.org/W2132737349","https://openalex.org/W2133564696","https://openalex.org/W2133941677","https://openalex.org/W2138243089","https://openalex.org/W2151197809","https://openalex.org/W2153579005","https://openalex.org/W2163605009","https://openalex.org/W2168231600","https://openalex.org/W2194775991","https://openalex.org/W2198724430","https://openalex.org/W2283214199","https://openalex.org/W2293634267","https://openalex.org/W2336650964","https://openalex.org/W2404068508","https://openalex.org/W2405883473","https://openalex.org/W2787894218","https://openalex.org/W2950133940","https://openalex.org/W2952033860","https://openalex.org/W2963750012","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W2626580042","https://openalex.org/W3048338200","https://openalex.org/W2806991962","https://openalex.org/W2962950660","https://openalex.org/W4400944702","https://openalex.org/W2803937730","https://openalex.org/W2911002035","https://openalex.org/W2942942367","https://openalex.org/W4293783896","https://openalex.org/W4226025883"],"abstract_inverted_index":{"With":[0],"the":[1,42,57,60,88,107,114,118,123,132,141,157],"fast":[2],"development":[3],"of":[4,44,91,96,106,117,159],"deep":[5],"learning,":[6],"it":[7],"has":[8],"become":[9],"common":[10],"to":[11,28,39,56,80,86,94,113],"learn":[12],"big":[13],"neural":[14],"networks":[15],"using":[16],"massive":[17],"training":[18],"data.":[19],"Asynchronous":[20],"Stochastic":[21],"Gradient":[22],"Descent":[23],"(ASGD)":[24],"is":[25,100],"widely":[26],"adopted":[27],"fulfill":[29],"this":[30,71,82],"task":[31],"for":[32],"its":[33,54],"efficiency,":[34],"which":[35],"is,":[36,48],"however,":[37],"known":[38],"suffer":[40],"from":[41],"problem":[43],"delayed":[45],"gradients.":[46],"That":[47],"when":[49],"a":[50,77],"local":[51],"worker":[52],"adds":[53],"gradient":[55,72,108],"global":[58,61],"model,":[59],"model":[62],"may":[63],"have":[64],"been":[65],"updated":[66],"by":[67,102],"other":[68],"workers":[69],"and":[70,110,137,140,151,154],"becomes":[73],"\"delayed\".":[74],"We":[75,121,130],"propose":[76],"novel":[78],"technology":[79],"compensate":[81],"delay,":[83],"so":[84],"as":[85],"make":[87],"optimization":[89],"behavior":[90],"ASGD":[92,128],"closer":[93],"that":[95,145],"sequential":[97,160],"SGD.":[98,161],"This":[99],"achieved":[101],"leveraging":[103],"Taylor":[104],"expansion":[105],"function":[109],"efficient":[111],"approximation":[112],"Hessian":[115],"matrix":[116],"loss":[119],"function.":[120],"call":[122],"new":[124],"algorithm":[125,134],"Delay":[126],"Compensated":[127],"(DC-ASGD).":[129],"evaluated":[131],"proposed":[133],"on":[135],"CIFAR-10":[136],"ImageNet":[138],"datasets,":[139],"experimental":[142],"results":[143],"demonstrate":[144],"DC-ASGD":[146],"outperforms":[147],"both":[148],"synchronous":[149],"SGD":[150],"asynchronous":[152],"SGD,":[153],"nearly":[155],"approaches":[156],"performance":[158]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":34},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":34},{"year":2021,"cited_by_count":50},{"year":2020,"cited_by_count":43},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-10-07T00:00:00"}