{"id":"https://openalex.org/W2963419707","doi":"https://doi.org/10.1162/neco_a_01088","title":"Distributed Newton Methods for Deep Neural Networks","display_name":"Distributed Newton Methods for Deep Neural Networks","publication_year":2018,"publication_date":"2018-04-13","ids":{"openalex":"https://openalex.org/W2963419707","doi":"https://doi.org/10.1162/neco_a_01088","mag":"2963419707","pmid":"https://pubmed.ncbi.nlm.nih.gov/29652589"},"language":"en","primary_location":{"id":"doi:10.1162/neco_a_01088","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_01088","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5013934000","display_name":"Chien-Chih Wang","orcid":"https://orcid.org/0000-0002-7869-3965"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chien-Chih Wang","raw_affiliation_strings":["Department of Computer Science, National Taiwan University, Taipei 10617, Taiwan","Department of Computer Science, National Taiwan University, Taipei 10617,\n Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Taiwan University, Taipei 10617, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Department of Computer Science, National Taiwan University, Taipei 10617,\n Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054253922","display_name":"Kent Loong Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Kent Loong Tan","raw_affiliation_strings":["Department of Computer Science, National Taiwan University, Taipei 10617, Taiwan","Department of Computer Science, National Taiwan University, Taipei 10617,\n Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Taiwan University, Taipei 10617, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Department of Computer Science, National Taiwan University, Taipei 10617,\n Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014490796","display_name":"Chun\u2010Ting Chen","orcid":"https://orcid.org/0000-0002-0930-0953"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chun-Ting Chen","raw_affiliation_strings":["Department of Computer Science, National Taiwan University, Taipei 10617, Taiwan","Department of Computer Science, National Taiwan University, Taipei 10617,\n Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Taiwan University, Taipei 10617, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Department of Computer Science, National Taiwan University, Taipei 10617,\n Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025122","display_name":"Yu-Hsiang Lin","orcid":"https://orcid.org/0000-0002-4765-324X"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yu-Hsiang Lin","raw_affiliation_strings":["Department of Physics, National Taiwan University, Taipei 10617, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Physics, National Taiwan University, Taipei 10617, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106708987","display_name":"S. Sathiya Keerthi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"S. Sathiya Keerthi","raw_affiliation_strings":["Criteo Research, Palo Alto, CA 94301, U.S.A"],"affiliations":[{"raw_affiliation_string":"Criteo Research, Palo Alto, CA 94301, U.S.A","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068664439","display_name":"Dhruv Mahajan","orcid":"https://orcid.org/0000-0002-1429-4551"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dhruv Mahajan","raw_affiliation_strings":["Facebook Research, Menlo Park, CA 94025, U.S.A"],"affiliations":[{"raw_affiliation_string":"Facebook Research, Menlo Park, CA 94025, U.S.A","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090165776","display_name":"S. Sundararajan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"S. Sundararajan","raw_affiliation_strings":["Microsoft Research India, Bangalore, Karnataka 56001, India"],"affiliations":[{"raw_affiliation_string":"Microsoft Research India, Bangalore, Karnataka 56001, India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068223640","display_name":"Chih\u2010Jen Lin","orcid":"https://orcid.org/0000-0003-4684-8747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chih-Jen Lin","raw_affiliation_strings":["Department of Computer Science, National Taiwan University, Taipei 10617, Taiwan","Department of Computer Science, National Taiwan University, Taipei 10617,\n Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Taiwan University, Taipei 10617, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Department of Computer Science, National Taiwan University, Taipei 10617,\n Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5013934000","https://openalex.org/A5014490796","https://openalex.org/A5054253922","https://openalex.org/A5068223640","https://openalex.org/A5068664439","https://openalex.org/A5090165776","https://openalex.org/A5102025122","https://openalex.org/A5106708987"],"corresponding_institution_ids":["https://openalex.org/I16733864","https://openalex.org/I4210124949"],"apc_list":null,"apc_paid":null,"fwci":1.9546,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.89838567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"30","issue":"6","first_page":"1673","last_page":"1724"},"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9988999962806702,"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/hessian-matrix","display_name":"Hessian matrix","score":0.6909377574920654},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6875292062759399},{"id":"https://openalex.org/keywords/jacobian-matrix-and-determinant","display_name":"Jacobian matrix and determinant","score":0.6121984720230103},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6020282506942749},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5285509824752808},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5236777663230896},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4961162507534027},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4463742971420288},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4136485457420349},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38116875290870667},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21122562885284424},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.12807098031044006}],"concepts":[{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.6909377574920654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6875292062759399},{"id":"https://openalex.org/C200331156","wikidata":"https://www.wikidata.org/wiki/Q506041","display_name":"Jacobian matrix and determinant","level":2,"score":0.6121984720230103},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6020282506942749},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5285509824752808},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5236777663230896},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4961162507534027},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4463742971420288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4136485457420349},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38116875290870667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21122562885284424},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.12807098031044006},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/neco_a_01088","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_01088","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:29652589","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29652589","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural computation","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W71081281","https://openalex.org/W104184427","https://openalex.org/W114517082","https://openalex.org/W196761320","https://openalex.org/W1533861849","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1830378420","https://openalex.org/W1932057668","https://openalex.org/W1988720110","https://openalex.org/W1991083751","https://openalex.org/W2006903949","https://openalex.org/W2087347434","https://openalex.org/W2100659887","https://openalex.org/W2102017903","https://openalex.org/W2103346443","https://openalex.org/W2105549957","https://openalex.org/W2107878631","https://openalex.org/W2112796928","https://openalex.org/W2125621954","https://openalex.org/W2130984546","https://openalex.org/W2131613942","https://openalex.org/W2132424367","https://openalex.org/W2142334564","https://openalex.org/W2153635508","https://openalex.org/W2157017541","https://openalex.org/W2160815625","https://openalex.org/W2164303766","https://openalex.org/W2226506202","https://openalex.org/W2335728318","https://openalex.org/W2410732425","https://openalex.org/W2559655401","https://openalex.org/W2559997609","https://openalex.org/W2594481151","https://openalex.org/W2596585349","https://openalex.org/W2604272474","https://openalex.org/W2604738573","https://openalex.org/W2913668833","https://openalex.org/W2949966795","https://openalex.org/W2962844195","https://openalex.org/W2964026016","https://openalex.org/W3028642772","https://openalex.org/W3120740533","https://openalex.org/W4238404964","https://openalex.org/W4293460823"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W2611031068","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W2350095335","https://openalex.org/W2544528198"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"involves":[2],"a":[3,9,20,55,72,130],"difficult":[4],"nonconvex":[5],"optimization":[6],"problem":[7],"with":[8,216],"large":[10,25],"number":[11],"of":[12,19,38,173,189,211],"weights":[13],"between":[14,144],"any":[15],"two":[16],"adjacent":[17],"layers":[18],"deep":[21,79,212],"structure.":[22],"To":[23],"handle":[24],"data":[26,86],"sets":[27],"or":[28],"complicated":[29],"networks,":[30],"distributed":[31,74,194,209],"training":[32,78,210],"is":[33,43,67,205,221],"needed,":[34],"but":[35],"the":[36,47,50,65,98,105,114,125,154,160,166,171,202,208],"calculation":[37],"function,":[39],"gradient,":[40],"and":[41,49,70,84,88,224],"Hessian":[42],"expensive.":[44],"In":[45,57],"particular,":[46],"communication":[48,126,143,161],"synchronization":[51,167],"cost":[52],"may":[53,225],"become":[54],"bottleneck.":[56],"this":[58],"letter,":[59],"we":[60,92,128,147,169],"focus":[61],"on":[62],"situations":[63],"where":[64],"model":[66],"distributedly":[68],"stored":[69],"propose":[71,129],"novel":[73],"Newton":[75,106,137,177],"method":[76,132,204],"for":[77,101,152,207],"neural":[80,213],"networks.":[81,214],"By":[82],"variable":[83],"feature-wise":[85],"partitions":[87],"some":[89,181,190],"careful":[90],"designs,":[91],"are":[93,110,196],"able":[94],"to":[95,112,123,164],"explicitly":[96],"use":[97],"Jacobian":[99],"matrix":[100],"matrix-vector":[102],"products":[103],"in":[104,193],"method.":[107],"Some":[108],"techniques":[109],"incorporated":[111],"reduce":[113,124,165],"running":[115,155],"time":[116,156],"as":[117,119,157,159],"well":[118,158],"memory":[120],"consumption.":[121],"First,":[122],"cost,":[127,168],"diagonalization":[131],"such":[133],"that":[134,201],"an":[135,175],"approximate":[136,176],"direction":[138,178],"can":[139],"be":[140],"obtained":[141],"without":[142],"machines.":[145],"Second,":[146],"consider":[148],"subsampled":[149],"Gauss-Newton":[150],"matrices":[151],"reducing":[153],"cost.":[162],"Third,":[163],"terminate":[170],"process":[172],"finding":[174],"even":[179],"though":[180],"nodes":[182],"have":[183],"not":[184],"finished":[185],"their":[186],"tasks.":[187],"Details":[188],"implementation":[191],"issues":[192],"environments":[195],"thoroughly":[197],"investigated.":[198],"Experiments":[199],"demonstrate":[200],"proposed":[203],"effective":[206],"Compared":[215],"stochastic":[217],"gradient":[218],"methods,":[219],"it":[220],"more":[222],"robust":[223],"give":[226],"better":[227],"test":[228],"accuracy.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}