{"id":"https://openalex.org/W2992646835","doi":"https://doi.org/10.1109/allerton.2019.8919735","title":"Byzantine Fault-Tolerant Parallelized Stochastic Gradient Descent for Linear Regression","display_name":"Byzantine Fault-Tolerant Parallelized Stochastic Gradient Descent for Linear Regression","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2992646835","doi":"https://doi.org/10.1109/allerton.2019.8919735","mag":"2992646835"},"language":"en","primary_location":{"id":"doi:10.1109/allerton.2019.8919735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2019.8919735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","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/A5054849639","display_name":"Nirupam Gupta","orcid":"https://orcid.org/0000-0003-4252-9319"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nirupam Gupta","raw_affiliation_strings":["Georgetown University,Department of Computer Science,Washington,DC,USA,20057","Department of Computer Science, Georgetown University, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"Georgetown University,Department of Computer Science,Washington,DC,USA,20057","institution_ids":["https://openalex.org/I184565670"]},{"raw_affiliation_string":"Department of Computer Science, Georgetown University, Washington, DC, USA","institution_ids":["https://openalex.org/I184565670"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042521435","display_name":"Nitin H. Vaidya","orcid":"https://orcid.org/0000-0001-5104-8977"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nitin H. Vaidya","raw_affiliation_strings":["Georgetown University,Department of Computer Science,Washington,DC,USA,20057","Department of Computer Science, Georgetown University, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"Georgetown University,Department of Computer Science,Washington,DC,USA,20057","institution_ids":["https://openalex.org/I184565670"]},{"raw_affiliation_string":"Department of Computer Science, Georgetown University, Washington, DC, USA","institution_ids":["https://openalex.org/I184565670"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054849639"],"corresponding_institution_ids":["https://openalex.org/I184565670"],"apc_list":null,"apc_paid":null,"fwci":1.5874,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.88128228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"415","last_page":"420"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9871000051498413,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9871000051498413,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9819999933242798,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9810000061988831,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/byzantine-fault-tolerance","display_name":"Byzantine fault tolerance","score":0.8173370957374573},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6752470135688782},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.6274673938751221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6203092336654663},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5389431715011597},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.5046719312667847},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5037626624107361},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4570394456386566},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.43767961859703064},{"id":"https://openalex.org/keywords/byzantine-architecture","display_name":"Byzantine architecture","score":0.4373202919960022},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.4180673360824585},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4117588996887207},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26010507345199585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23541346192359924},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.21357381343841553},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1388162076473236},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12720447778701782}],"concepts":[{"id":"https://openalex.org/C168021876","wikidata":"https://www.wikidata.org/wiki/Q1353446","display_name":"Byzantine fault tolerance","level":3,"score":0.8173370957374573},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6752470135688782},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.6274673938751221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6203092336654663},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5389431715011597},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.5046719312667847},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5037626624107361},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4570394456386566},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.43767961859703064},{"id":"https://openalex.org/C104562893","wikidata":"https://www.wikidata.org/wiki/Q47591","display_name":"Byzantine architecture","level":2,"score":0.4373202919960022},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.4180673360824585},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4117588996887207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26010507345199585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23541346192359924},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.21357381343841553},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1388162076473236},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12720447778701782},{"id":"https://openalex.org/C195244886","wikidata":"https://www.wikidata.org/wiki/Q41493","display_name":"Ancient history","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/allerton.2019.8919735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2019.8919735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W2053637704","https://openalex.org/W2132211083","https://openalex.org/W2166706236","https://openalex.org/W2402302915","https://openalex.org/W2614254310","https://openalex.org/W2752689052","https://openalex.org/W2783683139","https://openalex.org/W2789903762","https://openalex.org/W2789911054","https://openalex.org/W2790483052","https://openalex.org/W2913808958","https://openalex.org/W2923191059","https://openalex.org/W2964135521","https://openalex.org/W2964261056","https://openalex.org/W2964275427","https://openalex.org/W2964279249","https://openalex.org/W3017335724","https://openalex.org/W3137092842","https://openalex.org/W4212828114","https://openalex.org/W4241078790","https://openalex.org/W4289815854","https://openalex.org/W6684249991","https://openalex.org/W6712909570","https://openalex.org/W6743821447","https://openalex.org/W6748174344","https://openalex.org/W6748556508","https://openalex.org/W6748626757","https://openalex.org/W6748786018","https://openalex.org/W6754358263","https://openalex.org/W6760405771"],"related_works":["https://openalex.org/W2145120192","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4231621013","https://openalex.org/W4362706668","https://openalex.org/W3008318776","https://openalex.org/W2041416246","https://openalex.org/W3020853991"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,53,59,65,74,79,95,111,121,139,147],"problem":[4],"of":[5,27,40,58,68,76,94,120,127,130,149],"Byzantine":[6,43,45,69,131,150],"fault-tolerance":[7],"in":[8,78,125],"parallelized":[9,60,81,113],"stochastic":[10],"gradient":[11,89,97,105],"descent":[12],"(SGD)":[13],"method":[14,83,115],"solving":[15],"for":[16,138],"a":[17,23,28,36,85,101,117],"linear":[18],"regression":[19,122],"problem.":[20],"We":[21,108],"consider":[22],"synchronous":[24],"system":[25],"comprising":[26],"master":[29,54],"and":[30],"multiple":[31],"workers,":[32,71],"where":[33],"up":[34],"to":[35,52],"(known)":[37],"constant":[38],"number":[39],"workers":[41,47],"are":[42],"faulty.":[44],"faulty":[46,70,132,151],"may":[48],"send":[49],"incorrect":[50],"information":[51],"during":[55],"an":[56],"execution":[57],"SGD":[61,82,114],"method.":[62],"To":[63],"mitigate":[64],"detrimental":[66],"impact":[67],"we":[72],"replace":[73],"averaging":[75],"gradients":[77],"traditional":[80],"by":[84],"provably":[86],"more":[87],"robust":[88],"aggregation":[90,98],"rule.":[91],"The":[92,134],"crux":[93],"proposed":[96],"rule":[99],"is":[100],"gradient-filter,":[102],"named":[103],"comparative":[104],"clipping(CGC)":[106],"filter.":[107],"show":[109],"that":[110],"resultant":[112],"obtains":[116],"good":[118],"estimate":[119],"parameter":[123],"even":[124],"presence":[126],"bounded":[128],"fraction":[129,148],"workers.":[133,152],"upper":[135],"bound":[136],"derived":[137],"asymptotic":[140],"estimation":[141],"error":[142],"only":[143],"grows":[144],"linearly":[145],"with":[146]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2025-10-10T00:00:00"}