{"id":"https://openalex.org/W3134948707","doi":"https://doi.org/10.1109/tnnls.2021.3056947","title":"Faster Stochastic Quasi-Newton Methods","display_name":"Faster Stochastic Quasi-Newton Methods","publication_year":2021,"publication_date":"2021-03-05","ids":{"openalex":"https://openalex.org/W3134948707","doi":"https://doi.org/10.1109/tnnls.2021.3056947","mag":"3134948707","pmid":"https://pubmed.ncbi.nlm.nih.gov/33667166"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3056947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3056947","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","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/A5100760159","display_name":"Qingsong Zhang","orcid":"https://orcid.org/0000-0001-6626-6117"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]},{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qingsong Zhang","raw_affiliation_strings":["School of Electronic Engineering, Xidian University, Xi&#x2019;an, China","JD Tech, LLC, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"JD Tech, LLC, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033768689","display_name":"Feihu Huang","orcid":"https://orcid.org/0000-0003-0806-6074"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feihu Huang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015874725","display_name":"Cheng Deng","orcid":"https://orcid.org/0000-0003-2620-3247"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Deng","raw_affiliation_strings":["School of Electronic Engineering, Xidian University, Xi&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060016795","display_name":"Heng Huang","orcid":"https://orcid.org/0000-0002-3483-8333"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]},{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Huang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA","JD Finance American Corporation, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"JD Finance American Corporation, Mountain View, CA, USA","institution_ids":["https://openalex.org/I72427458"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100760159"],"corresponding_institution_ids":["https://openalex.org/I149594827","https://openalex.org/I4210103986"],"apc_list":null,"apc_paid":null,"fwci":2.3793,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90346969,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"33","issue":"9","first_page":"4388","last_page":"4397"},"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":0.9997000098228455,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"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/oracle","display_name":"Oracle","score":0.6638340950012207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6550328731536865},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6317158937454224},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5818779468536377},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.5642586350440979},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5202173590660095},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.494646281003952},{"id":"https://openalex.org/keywords/stochastic-neural-network","display_name":"Stochastic neural network","score":0.44628801941871643},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3798237442970276},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3667007088661194},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25496160984039307},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.243445485830307},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.09370091557502747}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6638340950012207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6550328731536865},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6317158937454224},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5818779468536377},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.5642586350440979},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5202173590660095},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.494646281003952},{"id":"https://openalex.org/C86582703","wikidata":"https://www.wikidata.org/wiki/Q7617824","display_name":"Stochastic neural network","level":4,"score":0.44628801941871643},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3798237442970276},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3667007088661194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25496160984039307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.243445485830307},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.09370091557502747},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3056947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3056947","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:33667166","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33667166","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":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4470460840","display_name":null,"funder_award_id":"2017YFE0104100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5089867355","display_name":null,"funder_award_id":"62071361","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1987083649","https://openalex.org/W2029463628","https://openalex.org/W2079705627","https://openalex.org/W2137515395","https://openalex.org/W2570983198","https://openalex.org/W2804009132","https://openalex.org/W2808381739","https://openalex.org/W2901838001","https://openalex.org/W2963941964","https://openalex.org/W2964000362","https://openalex.org/W2964303576","https://openalex.org/W2968543285","https://openalex.org/W2973370143","https://openalex.org/W2990138404","https://openalex.org/W3023496898","https://openalex.org/W3134948707","https://openalex.org/W3174935259","https://openalex.org/W4301014524","https://openalex.org/W6629536081","https://openalex.org/W6640275870","https://openalex.org/W6640590530","https://openalex.org/W6680610060","https://openalex.org/W6698038680","https://openalex.org/W6699273416","https://openalex.org/W6734509502","https://openalex.org/W6738096397","https://openalex.org/W6738155353","https://openalex.org/W6738699237","https://openalex.org/W6738931084","https://openalex.org/W6740708716","https://openalex.org/W6743395824","https://openalex.org/W6751658988","https://openalex.org/W6752458581","https://openalex.org/W6753122105","https://openalex.org/W6755084305","https://openalex.org/W6758762259","https://openalex.org/W6758969886","https://openalex.org/W6762577472","https://openalex.org/W6762954024","https://openalex.org/W6766611837","https://openalex.org/W6766675349","https://openalex.org/W6767560732","https://openalex.org/W6767864727","https://openalex.org/W6776854658"],"related_works":["https://openalex.org/W4286899070","https://openalex.org/W4323366756","https://openalex.org/W2913271688","https://openalex.org/W4234593354","https://openalex.org/W2893302333","https://openalex.org/W4285259204","https://openalex.org/W4389775782","https://openalex.org/W3207830353","https://openalex.org/W3109737792","https://openalex.org/W3150057971"],"abstract_inverted_index":{"Stochastic":[0],"optimization":[1,9],"methods":[2,45,65,79,89],"have":[3,66],"become":[4],"a":[5,54,71,108],"class":[6],"of":[7,121,135,176],"popular":[8],"tools":[10],"in":[11,137],"machine":[12,24],"learning.":[13],"Especially,":[14],"stochastic":[15,62,77,97,111],"gradient":[16],"descent":[17],"(SGD)":[18],"has":[19],"been":[20,67],"widely":[21],"used":[22],"for":[23,201],"learning":[25],"problems,":[26],"such":[27],"as":[28],"training":[29],"neural":[30],"networks,":[31],"due":[32],"to":[33,52,69,141,167],"low":[34],"per-iteration":[35],"computational":[36],"complexity.":[37,101],"In":[38],"fact,":[39],"the":[40,47,58,76,86,94,117,130,138,162,168,172,183],"Newton":[41],"or":[42],"quasi-newton":[43],"(QN)":[44],"leveraging":[46],"second-order":[48,83],"information":[49],"are":[50,165],"able":[51],"achieve":[53,70],"better":[55,72],"solution":[56,73],"than":[57,75],"first-order":[59,78,98],"methods.":[60],"Thus,":[61],"QN":[63,112],"(SQN)":[64],"developed":[68],"efficiently":[74],"by":[80],"utilizing":[81],"approximate":[82],"information.":[84],"However,":[85],"existing":[87,184],"SQN":[88],"still":[90],"do":[91],"not":[92],"reach":[93],"best":[95,131,185],"known":[96,132],"oracle":[99],"(SFO)":[100],"To":[102,148],"fill":[103],"this":[104],"gap,":[105],"we":[106,154],"propose":[107],"novel":[109],"faster":[110],"method":[113,128],"(SpiderSQN)":[114],"based":[115],"on":[116,189],"variance":[118],"reduced":[119],"technique":[120],"SIPDER.":[122],"We":[123],"prove":[124],"that":[125,194],"our":[126,195],"SpiderSQN":[127,156],"reaches":[129],"SFO":[133,174],"complexity":[134,175],"O(n+n<sup>1/2</sup>\u03f5<sup>-2</sup>)":[136],"finite-sum":[139],"setting":[140],"obtain":[142],"an":[143],"\u03f5":[144],"-first-order":[145],"stationary":[146],"point.":[147],"further":[149],"improve":[150],"its":[151],"practical":[152],"performance,":[153],"incorporate":[155],"with":[157],"different":[158],"momentum":[159],"schemes.":[160],"Moreover,":[161],"proposed":[163],"algorithms":[164,197],"generalized":[166],"online":[169],"setting,":[170],"and":[171],"corresponding":[173],"O(\u03f5<sup>-3</sup>)":[177],"is":[178],"developed,":[179],"which":[180],"also":[181],"matches":[182],"result.":[186],"Extensive":[187],"experiments":[188],"benchmark":[190],"data":[191],"sets":[192],"demonstrate":[193],"new":[196],"outperform":[198],"state-of-the-art":[199],"approaches":[200],"nonconvex":[202],"optimization.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}