{"id":"https://openalex.org/W4386815440","doi":"https://doi.org/10.14428/esann/2023.es2023-143","title":"Coordinate descent on the Stiefel manifold for deep neural network training","display_name":"Coordinate descent on the Stiefel manifold for deep neural network training","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386815440","doi":"https://doi.org/10.14428/esann/2023.es2023-143"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2023.es2023-143","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2023.es2023-143","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-143","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.14428/esann/2023.es2023-143","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011368095","display_name":"Estelle Massart","orcid":"https://orcid.org/0000-0003-4345-3096"},"institutions":[{"id":"https://openalex.org/I95674353","display_name":"UCLouvain","ror":"https://ror.org/02495e989","country_code":"BE","type":"education","lineage":["https://openalex.org/I95674353"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Estelle Massart","raw_affiliation_strings":["-UCLouvain -ICTEAM Avenue Georges Lematre 4, B-1348 Louvain-la-Neuve -Belgium","-UCLouvain -ICTEAM Avenue Georges Lema\u00eetre 4, B-1348 Louvain-la-Neuve -Belgium"],"affiliations":[{"raw_affiliation_string":"-UCLouvain -ICTEAM Avenue Georges Lematre 4, B-1348 Louvain-la-Neuve -Belgium","institution_ids":["https://openalex.org/I95674353"]},{"raw_affiliation_string":"-UCLouvain -ICTEAM Avenue Georges Lema\u00eetre 4, B-1348 Louvain-la-Neuve -Belgium","institution_ids":["https://openalex.org/I95674353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075520691","display_name":"Vinayak Abrol","orcid":"https://orcid.org/0000-0001-8149-8151"},"institutions":[{"id":"https://openalex.org/I110675161","display_name":"Infosys (India)","ror":"https://ror.org/03bs18y54","country_code":"IN","type":"company","lineage":["https://openalex.org/I110675161"]},{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinayak Abrol","raw_affiliation_strings":["-IIIT Delhi -CSE Department Infosys Centre for AI, R&D Block, IIIT Delhi -India"],"affiliations":[{"raw_affiliation_string":"-IIIT Delhi -CSE Department Infosys Centre for AI, R&D Block, IIIT Delhi -India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433","https://openalex.org/I110675161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011368095"],"corresponding_institution_ids":["https://openalex.org/I95674353"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10974336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"447","last_page":"452"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9969000220298767,"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"}},"topics":[{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9969000220298767,"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9957000017166138,"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":0.9898999929428101,"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/stiefel-manifold","display_name":"Stiefel manifold","score":0.9204717874526978},{"id":"https://openalex.org/keywords/coordinate-descent","display_name":"Coordinate descent","score":0.774983286857605},{"id":"https://openalex.org/keywords/geodesic","display_name":"Geodesic","score":0.7179490327835083},{"id":"https://openalex.org/keywords/orthogonality","display_name":"Orthogonality","score":0.7116747498512268},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.6742570400238037},{"id":"https://openalex.org/keywords/tangent-space","display_name":"Tangent space","score":0.6429381370544434},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5733165740966797},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5582202076911926},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.517593502998352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5143836140632629},{"id":"https://openalex.org/keywords/nonlinear-dimensionality-reduction","display_name":"Nonlinear dimensionality reduction","score":0.49347031116485596},{"id":"https://openalex.org/keywords/tangent-vector","display_name":"Tangent vector","score":0.4927850067615509},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.40492814779281616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3992511034011841},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3933538496494293},{"id":"https://openalex.org/keywords/tangent","display_name":"Tangent","score":0.2905753254890442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27510690689086914},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.2128380835056305},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.17591089010238647},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.14532417058944702},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.07044732570648193}],"concepts":[{"id":"https://openalex.org/C612670","wikidata":"https://www.wikidata.org/wiki/Q7616373","display_name":"Stiefel manifold","level":2,"score":0.9204717874526978},{"id":"https://openalex.org/C157553263","wikidata":"https://www.wikidata.org/wiki/Q5168004","display_name":"Coordinate descent","level":2,"score":0.774983286857605},{"id":"https://openalex.org/C165818556","wikidata":"https://www.wikidata.org/wiki/Q213488","display_name":"Geodesic","level":2,"score":0.7179490327835083},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.7116747498512268},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.6742570400238037},{"id":"https://openalex.org/C157157409","wikidata":"https://www.wikidata.org/wiki/Q909601","display_name":"Tangent space","level":2,"score":0.6429381370544434},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5733165740966797},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5582202076911926},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.517593502998352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5143836140632629},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.49347031116485596},{"id":"https://openalex.org/C47890412","wikidata":"https://www.wikidata.org/wiki/Q1179296","display_name":"Tangent vector","level":3,"score":0.4927850067615509},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.40492814779281616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3992511034011841},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3933538496494293},{"id":"https://openalex.org/C138187205","wikidata":"https://www.wikidata.org/wiki/Q131251","display_name":"Tangent","level":2,"score":0.2905753254890442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27510690689086914},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.2128380835056305},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.17591089010238647},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.14532417058944702},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.07044732570648193},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14428/esann/2023.es2023-143","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2023.es2023-143","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-143","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},{"id":"pmh:oai:dial.uclouvain.be:boreal:289245","is_oa":true,"landing_page_url":"http://hdl.handle.net/2078.1/289245","pdf_url":null,"source":{"id":"https://openalex.org/S4306401902","display_name":"Digital Access to Libraries (Universit\u00e9 catholique de Louvain (UCL), l'Universit\u00e9 de Namur (UNamur) and the Universit\u00e9 Saint-Louis (USL-B))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I95674353","host_organization_name":"UCLouvain","host_organization_lineage":["https://openalex.org/I95674353"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.14428/esann/2023.es2023-143","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2023.es2023-143","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-143","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G707059429","display_name":null,"funder_award_id":"MFIRP","funder_id":"https://openalex.org/F4320324473","funder_display_name":"Indian Institute of Technology Delhi"}],"funders":[{"id":"https://openalex.org/F4320321390","display_name":"Fonds De La Recherche Scientifique - FNRS","ror":"https://ror.org/03q83t159"},{"id":"https://openalex.org/F4320322753","display_name":"Infosys Foundation","ror":"https://ror.org/03bs18y54"},{"id":"https://openalex.org/F4320324473","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06"},{"id":"https://openalex.org/F4320330597","display_name":"Indraprastha Institute of Information Technology, Delhi","ror":"https://ror.org/03vfp4g33"},{"id":"https://openalex.org/F4320335277","display_name":"National Physical Laboratory","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386815440.pdf","grobid_xml":"https://content.openalex.org/works/W4386815440.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2045512849","https://openalex.org/W2144112446","https://openalex.org/W2175402905","https://openalex.org/W2896801757","https://openalex.org/W2963103976","https://openalex.org/W2981748719","https://openalex.org/W2995455260","https://openalex.org/W2995941914","https://openalex.org/W2996609754","https://openalex.org/W2998843058","https://openalex.org/W3034206445","https://openalex.org/W3035757170","https://openalex.org/W3163158867","https://openalex.org/W3192210946","https://openalex.org/W4221146247","https://openalex.org/W4225674648","https://openalex.org/W4287871765","https://openalex.org/W4288009529","https://openalex.org/W4297069215","https://openalex.org/W6685537299","https://openalex.org/W6762993288","https://openalex.org/W6775828767"],"related_works":["https://openalex.org/W2126146080","https://openalex.org/W1903999421","https://openalex.org/W2021661079","https://openalex.org/W2361271799","https://openalex.org/W2118957867","https://openalex.org/W3105578323","https://openalex.org/W1598317013","https://openalex.org/W4249328994","https://openalex.org/W2041785029","https://openalex.org/W70452321"],"abstract_inverted_index":{"To":[0],"alleviate":[1],"the":[2,21,29,39,47],"cost":[3],"incurred":[4],"by":[5,64],"orthogonality":[6],"constraints":[7],"in":[8,60],"optimization":[9],"and":[10,42],"model":[11],"training,":[12],"we":[13],"propose":[14],"a":[15],"stochastic":[16],"coordinate":[17,53],"descent":[18,54],"algorithm":[19,70],"on":[20,28,71],"Stiefel":[22,30],"manifold.We":[23],"compute":[24],"expressions":[25],"for":[26],"geodesics":[27],"manifold":[31],"with":[32,36],"initial":[33],"velocity":[34],"aligned":[35],"coordinates":[37],"of":[38,52,62],"tangent":[40],"space":[41],"show":[43],"that,":[44],"analogously":[45],"to":[46],"orthogonal":[48],"group,":[49],"iterate":[50],"updates":[51],"methods":[55],"can":[56],"be":[57],"efficiently":[58],"implemented":[59],"terms":[61],"multiplications":[63],"Givens":[65],"matrices.We":[66],"illustrate":[67],"our":[68],"proposed":[69],"deep":[72],"neural":[73],"network":[74],"training.":[75]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}