{"id":"https://openalex.org/W2542929316","doi":"https://doi.org/10.48550/arxiv.1610.06664","title":"Stochastic Gradient MCMC with Stale Gradients","display_name":"Stochastic Gradient MCMC with Stale Gradients","publication_year":2016,"publication_date":"2016-10-21","ids":{"openalex":"https://openalex.org/W2542929316","doi":"https://doi.org/10.48550/arxiv.1610.06664","mag":"2542929316"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1610.06664","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1610.06664","pdf_url":"https://arxiv.org/pdf/1610.06664","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/1610.06664","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114686221","display_name":"Changyou Chen","orcid":"https://orcid.org/0000-0002-9877-8448","observed_orcids":["https://orcid.org/0000-0002-9877-8448"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Changyou","raw_affiliation_strings":["Google Inc. , Venice , CA , USA","Duke University, Durham, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc. , Venice , CA , USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Duke University, Durham, United States","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101558275","display_name":"Nan Ding","orcid":"https://orcid.org/0000-0003-2515-1692","observed_orcids":["https://orcid.org/0000-0003-2515-1692"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ding, Nan","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering , Duke University , Durham , NC , USA","Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering , Duke University , Durham , NC , USA","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101417967","display_name":"Chunyuan Li","orcid":"https://orcid.org/0000-0003-1271-9605","observed_orcids":["https://orcid.org/0000-0003-1271-9605","https://orcid.org/0000-0002-8293-8785"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Chunyuan","raw_affiliation_strings":["Google Inc. , Venice , CA , USA","Duke University, Durham, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc. , Venice , CA , USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Duke University, Durham, United States","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101959000","display_name":"Yizhe Zhang","orcid":"https://orcid.org/0000-0002-9599-7995","observed_orcids":["https://orcid.org/0000-0002-9599-7995"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Yizhe","raw_affiliation_strings":["Google Inc. , Venice , CA , USA","Duke University, Durham, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc. , Venice , CA , USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Duke University, Durham, United States","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016448581","display_name":"Lawrence Carin","orcid":"https://orcid.org/0000-0001-6277-7948","observed_orcids":["https://orcid.org/0000-0001-6277-7948"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carin, Lawrence","raw_affiliation_strings":["Google Inc. , Venice , CA , USA","Duke University, Durham, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc. , Venice , CA , USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Duke University, Durham, United States","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":17,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9692000150680542,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9692000150680542,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.027300000190734863,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.0015999999595806003,"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/stochastic-gradient-mcmc","display_name":"stochastic gradient MCMC","score":0.9980000257492065},{"id":"https://openalex.org/keywords/asynchronous-computation","display_name":"asynchronous computation","score":0.5220000147819519},{"id":"https://openalex.org/keywords/estimation-variance","display_name":"estimation variance","score":0.8420000076293945},{"id":"https://openalex.org/keywords/convergence-properties","display_name":"convergence properties","score":0.6710000038146973},{"id":"https://openalex.org/keywords/linear-speedup","display_name":"linear speedup","score":0.7329999804496765}],"concepts":[{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.8733686208724976},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.705810546875},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6812061071395874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5860891342163086},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5737985372543335},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5333400368690491},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5196589231491089},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42673683166503906},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.41953206062316895},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.408966064453125},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3001742959022522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2690916657447815},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.07582977414131165},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1610.06664","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1610.06664","pdf_url":"https://arxiv.org/pdf/1610.06664","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:2542929316","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1610.06664.pdf","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.1610.06664","doi":"https://doi.org/10.48550/arxiv.1610.06664","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1610.06664","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1610.06664","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1610.06664","pdf_url":"https://arxiv.org/pdf/1610.06664","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":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2542929316.pdf","grobid_xml":"https://content.openalex.org/works/W2542929316.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W3401598","https://openalex.org/W586414279","https://openalex.org/W605753744","https://openalex.org/W1524172054","https://openalex.org/W1568229137","https://openalex.org/W1586766433","https://openalex.org/W1845277745","https://openalex.org/W2101893470","https://openalex.org/W2132737349","https://openalex.org/W2138243089","https://openalex.org/W2138996412","https://openalex.org/W2144193737","https://openalex.org/W2145536610","https://openalex.org/W2165652770","https://openalex.org/W2167433878","https://openalex.org/W2168231600","https://openalex.org/W2186210550","https://openalex.org/W2186615578","https://openalex.org/W2188647300","https://openalex.org/W2202981647","https://openalex.org/W2528137865","https://openalex.org/W2949585412","https://openalex.org/W2950942124","https://openalex.org/W2951266961","https://openalex.org/W2952033860","https://openalex.org/W2963942415","https://openalex.org/W7098642242"],"related_works":["https://openalex.org/W3019065887","https://openalex.org/W2963554070","https://openalex.org/W2519863647","https://openalex.org/W2556547645","https://openalex.org/W3007353463","https://openalex.org/W2940715532","https://openalex.org/W2635018027","https://openalex.org/W2523496727","https://openalex.org/W7161062430","https://openalex.org/W2905549570"],"abstract_inverted_index":{"Stochastic":[0],"gradient":[1],"MCMC":[2],"(SG-MCMC)":[3],"has":[4,62],"played":[5],"an":[6,82],"important":[7],"role":[8],"in":[9,55],"large-scale":[10],"Bayesian":[11,114],"learning,":[12],"with":[13,117,165],"well-developed":[14],"theoretical":[15],"convergence":[16,60],"properties.":[17],"In":[18,67,111],"such":[19],"applications":[20],"of":[21,81,89,105,109,128,139,145,163],"SG-MCMC,":[22,56,118],"it":[23],"is":[24,107],"becoming":[25],"increasingly":[26],"popular":[27],"to":[28,73,96],"employ":[29],"distributed":[30,115],"systems,":[31],"where":[32,119],"stochastic":[33,90],"gradients":[34,50,121],"are":[35,44,122],"computed":[36,123],"based":[37,100],"on":[38,59,86,101,136,148],"some":[39],"outdated":[40],"parameters,":[41],"yielding":[42],"what":[43],"termed":[45],"stale":[46,49,120,166],"gradients.":[47,167],"While":[48],"could":[51],"be":[52],"directly":[53],"used":[54],"their":[57],"impact":[58],"properties":[61],"not":[63],"been":[64],"well":[65],"studied.":[66],"this":[68],"paper":[69],"we":[70],"develop":[71],"theory":[72,131],"show":[74],"that":[75],"while":[76],"the":[77,87,97,137,143,159],"bias":[78],"and":[79,151,161],"MSE":[80],"SG-MCMC":[83,164],"algorithm":[84],"depend":[85],"staleness":[88],"gradients,":[91],"its":[92],"estimation":[93,140],"variance":[94,141],"(relative":[95],"expected":[98],"estimate,":[99],"a":[102,112,126,133],"prescribed":[103],"number":[104,144],"samples)":[106],"independent":[108],"it.":[110],"simple":[113],"system":[116],"asynchronously":[124],"by":[125],"set":[127],"workers,":[129],"our":[130,156],"indicates":[132],"linear":[134],"speedup":[135],"decrease":[138],"w.r.t.":[142],"workers.":[146],"Experiments":[147],"synthetic":[149],"data":[150],"deep":[152],"neural":[153],"networks":[154],"validate":[155],"theory,":[157],"demonstrating":[158],"effectiveness":[160],"scalability":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-11-04T00:00:00"}