{"id":"https://openalex.org/W4389252608","doi":"https://doi.org/10.1109/tnnls.2023.3326177","title":"Stochastic Optimization for Nonconvex Problem With Inexact Hessian Matrix, Gradient, and Function","display_name":"Stochastic Optimization for Nonconvex Problem With Inexact Hessian Matrix, Gradient, and Function","publication_year":2023,"publication_date":"2023-12-01","ids":{"openalex":"https://openalex.org/W4389252608","doi":"https://doi.org/10.1109/tnnls.2023.3326177","pmid":"https://pubmed.ncbi.nlm.nih.gov/38039170"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3326177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3326177","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/A5100324286","display_name":"Liu Liu","orcid":"https://orcid.org/0000-0002-8128-2788"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu Liu","raw_affiliation_strings":["Institute of Artificial Intelligence and the State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8128-2788","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and the State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005915688","display_name":"Xuanqing Liu","orcid":"https://orcid.org/0000-0002-0328-6708"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuanqing Liu","raw_affiliation_strings":["Amazon Web Services (AWS), Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services (AWS), Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010841999","display_name":"Cho\u2010Jui Hsieh","orcid":"https://orcid.org/0000-0002-3520-9627"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cho-Jui Hsieh","raw_affiliation_strings":["Department of Computer Science, University of California at Los Angeles, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California at Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["School of Computer Science, Sydney AI Centre, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia","Sydney AI Centre, Faculty of Engineering, School of Computer Science, The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7225-5449","affiliations":[{"raw_affiliation_string":"School of Computer Science, Sydney AI Centre, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"Sydney AI Centre, Faculty of Engineering, School of Computer Science, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6345,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74221248,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"36","issue":"1","first_page":"1651","last_page":"1663"},"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9993000030517578,"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/T12676","display_name":"Machine Learning and ELM","score":0.9433000087738037,"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":0.9574254751205444},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5963332653045654},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5315693616867065},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5123494863510132},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4701074957847595},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4647371768951416},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.46323320269584656},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.45562174916267395},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4342803955078125},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43183666467666626},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4152626097202301},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32970044016838074},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.15695089101791382}],"concepts":[{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.9574254751205444},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5963332653045654},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5315693616867065},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5123494863510132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4701074957847595},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4647371768951416},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.46323320269584656},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.45562174916267395},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4342803955078125},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43183666467666626},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4152626097202301},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32970044016838074},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.15695089101791382},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3326177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3326177","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:38039170","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38039170","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W71081281","https://openalex.org/W147998453","https://openalex.org/W1991083751","https://openalex.org/W1994974865","https://openalex.org/W2009941369","https://openalex.org/W2040466831","https://openalex.org/W2042465463","https://openalex.org/W2043674215","https://openalex.org/W2051669046","https://openalex.org/W2091825929","https://openalex.org/W2124541940","https://openalex.org/W2137198385","https://openalex.org/W2137633966","https://openalex.org/W2156005216","https://openalex.org/W2166163936","https://openalex.org/W2546420264","https://openalex.org/W2795347428","https://openalex.org/W2894719012","https://openalex.org/W2896830491","https://openalex.org/W2950311990","https://openalex.org/W2963231446","https://openalex.org/W2963307318","https://openalex.org/W2963465983","https://openalex.org/W2988898191","https://openalex.org/W2997803752","https://openalex.org/W3023674141","https://openalex.org/W3030916542","https://openalex.org/W3135262686","https://openalex.org/W3184878065","https://openalex.org/W4200225801","https://openalex.org/W4206659778","https://openalex.org/W4224036449","https://openalex.org/W4244670803","https://openalex.org/W6640256981","https://openalex.org/W6640915965","https://openalex.org/W6676105031","https://openalex.org/W6680196509","https://openalex.org/W6698038680","https://openalex.org/W6713469626","https://openalex.org/W6734280532","https://openalex.org/W6735923916","https://openalex.org/W6738155353","https://openalex.org/W6740708716","https://openalex.org/W6745438911","https://openalex.org/W6757257686","https://openalex.org/W6765409018","https://openalex.org/W6811379374","https://openalex.org/W6838772106","https://openalex.org/W6842558655"],"related_works":["https://openalex.org/W2611031068","https://openalex.org/W1704347466","https://openalex.org/W1996936972","https://openalex.org/W4283017538","https://openalex.org/W4221162014","https://openalex.org/W2169345436","https://openalex.org/W2053964895","https://openalex.org/W2952728270","https://openalex.org/W4309210394","https://openalex.org/W2130502925"],"abstract_inverted_index":{"Trust":[0],"region":[1],"(TR)":[2],"and":[3,27,36,69,85,99,155],"adaptive":[4],"regularization":[5],"using":[6],"cubics":[7],"(ARC)":[8],"have":[9,12],"proven":[10],"to":[11,30,52,107],"some":[13],"very":[14],"appealing":[15],"theoretical":[16],"properties":[17],"for":[18],"nonconvex":[19,150],"optimization":[20],"by":[21,135],"concurrently":[22],"computing":[23],"function":[24,86],"value,":[25],"gradient,":[26,84],"Hessian":[28,82],"matrix":[29],"obtain":[31],"the":[32,37,46,55,81,104,114,118,127,142,159],"next":[33],"search":[34],"direction":[35],"adjusted":[38],"parameters.":[39],"Although":[40],"stochastic":[41,66,70],"approximations":[42],"help":[43],"largely":[44],"reduce":[45],"computational":[47,171],"cost,":[48],"it":[49],"is":[50,112],"challenging":[51],"theoretically":[53],"guarantee":[54],"convergence":[56],"rate.":[57],"In":[58,125],"this":[59],"article,":[60],"we":[61],"explore":[62],"a":[63,137,149,162],"family":[64],"of":[65,80,113,165],"TR":[67,98],"(STR)":[68],"ARC":[71],"(SARC)":[72],"methods":[73],"that":[74,103],"can":[75,132],"simultaneously":[76],"provide":[77],"inexact":[78],"computations":[79,120],"matrix,":[83],"values.":[87],"Our":[88],"algorithms":[89,168],"require":[90,169],"much":[91],"fewer":[92],"propagations":[93],"overhead":[94,172],"per":[95,173],"iteration":[96,105,174],"than":[97,175],"ARC.":[100],"We":[101],"prove":[102],"complexity":[106],"achieve":[108],"-approximate":[109],"second-order":[110,177],"optimality":[111],"same":[115,160],"order":[116],"as":[117],"exact":[119],"demonstrated":[121],"in":[122,141],"previous":[123],"studies.":[124],"addition,":[126],"mild":[128],"conditions":[129],"on":[130],"inexactness":[131],"be":[133],"met":[134],"leveraging":[136],"random":[138],"sampling":[139],"technology":[140],"finite-sum":[143],"minimization":[144],"problem.":[145],"Numerical":[146],"experiments":[147],"with":[148,158],"problem":[151],"support":[152],"these":[153],"findings":[154],"demonstrate":[156],"that,":[157],"or":[161],"similar":[163],"number":[164],"iterations,":[166],"our":[167],"less":[170],"current":[176],"methods.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}