{"id":"https://openalex.org/W3147200261","doi":"https://doi.org/10.1109/cdc45484.2021.9682842","title":"Neural Network Training as an Optimal Control Problem : \u2014 An Augmented Lagrangian Approach \u2014","display_name":"Neural Network Training as an Optimal Control Problem : \u2014 An Augmented Lagrangian Approach \u2014","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W3147200261","doi":"https://doi.org/10.1109/cdc45484.2021.9682842","mag":"3147200261"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9682842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9682842","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.14343","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019280099","display_name":"Brecht Evens","orcid":"https://orcid.org/0000-0002-2317-9395"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Brecht Evens","raw_affiliation_strings":["Department of Electrical Engineering ESAT-STADIUS, Leuven, Belgium","Katholieke Universiteit Leuven"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering ESAT-STADIUS, Leuven, Belgium","institution_ids":[]},{"raw_affiliation_string":"Katholieke Universiteit Leuven","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060005608","display_name":"Puya Latafat","orcid":"https://orcid.org/0000-0002-7969-8565"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Puya Latafat","raw_affiliation_strings":["Department of Electrical Engineering ESAT-STADIUS, Leuven, Belgium","Katholieke Universiteit Leuven"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering ESAT-STADIUS, Leuven, Belgium","institution_ids":[]},{"raw_affiliation_string":"Katholieke Universiteit Leuven","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010064441","display_name":"Andreas Themelis","orcid":"https://orcid.org/0000-0002-6044-0169"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Andreas Themelis","raw_affiliation_strings":["Faculty of Information Science and Electrical Engineering (ISEE), Fukuoka, Japan","Katholieke Universiteit Leuven"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Electrical Engineering (ISEE), Fukuoka, Japan","institution_ids":[]},{"raw_affiliation_string":"Katholieke Universiteit Leuven","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078854904","display_name":"Johan A. K. Suykens","orcid":"https://orcid.org/0000-0002-8846-6352"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Johan Suykens","raw_affiliation_strings":["Department of Electrical Engineering ESAT-STADIUS, Leuven, Belgium","Katholieke Universiteit Leuven"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering ESAT-STADIUS, Leuven, Belgium","institution_ids":[]},{"raw_affiliation_string":"Katholieke Universiteit Leuven","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031380765","display_name":"Panagiotis Patrinos","orcid":"https://orcid.org/0000-0003-4824-7697"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Panagiotis Patrinos","raw_affiliation_strings":["Department of Electrical Engineering ESAT-STADIUS, Leuven, Belgium","Kyushu University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering ESAT-STADIUS, Leuven, Belgium","institution_ids":[]},{"raw_affiliation_string":"Kyushu University","institution_ids":["https://openalex.org/I135598925"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5136","last_page":"5143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9993000030517578,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9993000030517578,"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":0.9984999895095825,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/artificial-neural-network","display_name":"Artificial neural network","score":0.7451492547988892},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.6815065741539001},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6391947269439697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6188324093818665},{"id":"https://openalex.org/keywords/augmented-lagrangian-method","display_name":"Augmented Lagrangian method","score":0.5953781604766846},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5825431942939758},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4124152958393097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34110286831855774},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3146824240684509},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24237248301506042}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7451492547988892},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.6815065741539001},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6391947269439697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6188324093818665},{"id":"https://openalex.org/C150452318","wikidata":"https://www.wikidata.org/wiki/Q4820432","display_name":"Augmented Lagrangian method","level":2,"score":0.5953781604766846},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5825431942939758},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4124152958393097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34110286831855774},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3146824240684509},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24237248301506042}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/cdc45484.2021.9682842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9682842","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.14343","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.14343","pdf_url":"https://arxiv.org/pdf/2103.14343","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/726923","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/726923","pdf_url":"https://lirias.kuleuven.be/retrieve/ca45e7de-8a10-43cd-a3dd-833cd9392dba","source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"60th IEEE Conference on Decision and Control, Austin, Texas, 13-17 December 2021","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:3147200261","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.14343.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"pmh:oai:catalog.lib.kyushu-u.ac.jp:2324/4785491","is_oa":true,"landing_page_url":"http://hdl.handle.net/2324/4785491","pdf_url":null,"source":{"id":"https://openalex.org/S4306400832","display_name":"Kyushu University Institutional Repository (QIR) (Kyushu University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I135598925","host_organization_name":"Kyushu University","host_organization_lineage":["https://openalex.org/I135598925"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"0743-1546","raw_type":"conference paper"},{"id":"pmh:oai:irdb.nii.ac.jp:01211:0005988192","is_oa":true,"landing_page_url":"https://hdl.handle.net/2324/4785491","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Conference on Decision and Control (CDC)","raw_type":"conference paper"},{"id":"doi:10.48550/arxiv.2103.14343","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.14343","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.14343","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.14343","pdf_url":"https://arxiv.org/pdf/2103.14343","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[{"id":"https://openalex.org/G2787453302","display_name":"Structured Low-Rank matrix / tensor approximation: numerical optimization-based algorithms and applications","funder_award_id":"30468160","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G2834563790","display_name":"A unifying algorithmic framework for structured optimization","funder_award_id":"G086518N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G3100133282","display_name":null,"funder_award_id":"1196820N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G3408909379","display_name":null,"funder_award_id":"JP21K17710","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4231125181","display_name":"New-generation optimization algorithms for engineering","funder_award_id":"21K17710","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4483643987","display_name":"Learning to optimize nonconvex problems: provably and efficiently","funder_award_id":"G0A0920N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G4829754272","display_name":null,"funder_award_id":"C14/18/068","funder_id":"https://openalex.org/F4320322308","funder_display_name":"KU Leuven"},{"id":"https://openalex.org/G623480064","display_name":"Risk-averse Control and Dynamic Optimization: Bridging the Gap Between Robust and Stochastic Control","funder_award_id":"G086318N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G7564167306","display_name":null,"funder_award_id":"30468160","funder_id":"https://openalex.org/F4320321390","funder_display_name":"Fonds De La Recherche Scientifique - FNRS"}],"funders":[{"id":"https://openalex.org/F4320321390","display_name":"Fonds De La Recherche Scientifique - FNRS","ror":"https://ror.org/03q83t159"},{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320322308","display_name":"KU Leuven","ror":"https://ror.org/05f950310"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W646582900","https://openalex.org/W1498436455","https://openalex.org/W1522301498","https://openalex.org/W1543439990","https://openalex.org/W1597009674","https://openalex.org/W1833744030","https://openalex.org/W2089024363","https://openalex.org/W2095705004","https://openalex.org/W2144513243","https://openalex.org/W2194775991","https://openalex.org/W2271840356","https://openalex.org/W2769449302","https://openalex.org/W2798766386","https://openalex.org/W2949117887","https://openalex.org/W2949650786","https://openalex.org/W2949966795","https://openalex.org/W2951136802","https://openalex.org/W2962817490","https://openalex.org/W2963055445","https://openalex.org/W2965794435","https://openalex.org/W3003257820","https://openalex.org/W3036100489","https://openalex.org/W3037884961","https://openalex.org/W3037950864","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6681151457","https://openalex.org/W6694517276","https://openalex.org/W6696761078","https://openalex.org/W6705072498","https://openalex.org/W6743750086","https://openalex.org/W6756290669","https://openalex.org/W6764304558"],"related_works":["https://openalex.org/W1494003781","https://openalex.org/W1978705733","https://openalex.org/W1502632589","https://openalex.org/W2968881461","https://openalex.org/W2268592","https://openalex.org/W1938113357","https://openalex.org/W3086296376","https://openalex.org/W1739346054","https://openalex.org/W2022760140","https://openalex.org/W3122516027","https://openalex.org/W3046107682","https://openalex.org/W3157391631","https://openalex.org/W2803770487","https://openalex.org/W2773708962","https://openalex.org/W1495166627","https://openalex.org/W2056731402","https://openalex.org/W2511582908","https://openalex.org/W3118397459","https://openalex.org/W2999005620","https://openalex.org/W2470835101"],"abstract_inverted_index":{"Training":[0],"of":[1,117,141,163],"neural":[2,118,142],"networks":[3],"amounts":[4,45],"to":[5,46,52,71,101,106,114,130],"nonconvex":[6],"optimization":[7],"problems":[8,148],"that":[9,66,95,123],"are":[10,128,149],"typically":[11,83],"solved":[12,132],"by":[13,30,86,151],"using":[14,133],"backpropagation":[15,44],"and":[16,73],"(variants":[17],"of)":[18],"stochastic":[19],"gradient":[20],"descent.":[21],"In":[22],"this":[23,42,75,87,112],"work,":[24],"we":[25],"propose":[26],"an":[27,89,98,153],"alternative":[28],"approach":[29,49,79,154],"viewing":[31],"the":[32,47,56,77,102,115,124,139,144,161],"training":[33,116],"task":[34],"as":[35],"a":[36,107],"nonlinear":[37],"optimal":[38,53],"control":[39],"problem.":[40],"Under":[41],"lens,":[43],"sequential":[48],"(single":[50],"shooting)":[51,81],"control,":[54],"where":[55],"states":[57],"variables":[58],"have":[59],"been":[60],"eliminated.":[61],"It":[62],"is":[63,82,93,121,166],"well":[64],"known":[65],"single":[67],"shooting":[68],"may":[69],"lead":[70],"ill-conditioning,":[72],"for":[74],"reason":[76],"simultaneous":[78],"(multiple":[80],"preferred.":[84],"Motivated":[85],"hypothesis,":[88],"augmented":[90],"Lagrangian":[91,103,126],"algorithm":[92],"developed":[94],"only":[96],"requires":[97],"approximate":[99],"solution":[100],"subproblems":[104,127],"up":[105],"user-defined":[108],"accuracy.":[109],"By":[110],"applying":[111],"framework":[113],"networks,":[119,143],"it":[120],"shown":[122],"inner":[125],"amenable":[129],"be":[131],"Gauss-Newton":[134],"iterations.":[135],"To":[136],"fully":[137],"exploit":[138],"structure":[140],"resulting":[145],"linear":[146],"least-squares":[147],"addressed":[150],"employing":[152],"based":[155],"on":[156,168],"forward":[157],"dynamic":[158],"programming.":[159],"Finally,":[160],"effectiveness":[162],"our":[164],"method":[165],"showcased":[167],"regression":[169],"datasets.":[170]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}