{"id":"https://openalex.org/W2995869484","doi":null,"title":"Prox-SGD: Training Structured Neural Networks under Regularization and Constraints","display_name":"Prox-SGD: Training Structured Neural Networks under Regularization and Constraints","publication_year":2020,"publication_date":"2020-04-30","ids":{"openalex":"https://openalex.org/W2995869484","mag":"2995869484"},"language":"en","primary_location":{"id":"pmh:oai:orbilu.uni.lu:10993/45122","doi":null,"is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/45122","pdf_url":"http://orbilu.uni.lu/handle/10993/45122","source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"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":"International Conference on Learning Representations (ICLR) 2020 (2020); International Conference on Learning Representations (ICLR) 2020, 30-04-2020","raw_type":"http://purl.org/coar/resource_type/c_5794"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://orbilu.uni.lu/handle/10993/45122","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100397568","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-3530-3525","observed_orcids":["https://orcid.org/0000-0002-3530-3525","https://orcid.org/0000-0001-5852-6345"]},"institutions":[{"id":"https://openalex.org/I4923324","display_name":"Fraunhofer-Gesellschaft","ror":"https://ror.org/05hkkdn48","country_code":"DE","type":"government","lineage":["https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Fraunhofer Society, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3530-3525","affiliations":[{"raw_affiliation_string":"Fraunhofer Society, Munich, Germany","institution_ids":["https://openalex.org/I4923324"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060048483","display_name":"Yaxiong Yuan","orcid":"https://orcid.org/0000-0002-4118-039X","observed_orcids":["https://orcid.org/0000-0002-4118-039X"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Yaxiong Yuan","raw_affiliation_strings":["University of Luxembourg, Luxembourg, Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034877807","display_name":"Avraam Chatzimichailidis","orcid":"https://orcid.org/0000-0002-7577-7995","observed_orcids":["https://orcid.org/0000-0002-7577-7995"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Avraam Chatzimichailidis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042985821","display_name":"Ruud J. G. van Sloun","orcid":"https://orcid.org/0000-0003-2845-0495","observed_orcids":["https://orcid.org/0000-0003-2845-0495"]},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ruud J. G. van Sloun","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-2845-0495","affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Lei","orcid":"https://orcid.org/0000-0002-9144-0559","observed_orcids":["https://orcid.org/0000-0002-9144-0559"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Lei Lei","raw_affiliation_strings":["University of Luxembourg, Luxembourg, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0002-9144-0559","affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016154330","display_name":"Symeon Chatzinotas","orcid":"https://orcid.org/0000-0001-5122-0001","observed_orcids":["https://orcid.org/0000-0001-5122-0001"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Symeon Chatzinotas","raw_affiliation_strings":["University of Luxembourg, Luxembourg, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0001-5122-0001","affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7198,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.73567463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9951000213623047,"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":0.9951000213623047,"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":0.0015999999595806003,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.0010000000474974513,"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/structured-neural-networks","display_name":"structured neural networks","score":0.9850000143051147},{"id":"https://openalex.org/keywords/nonsmooth-optimization","display_name":"nonsmooth optimization","score":0.8889999985694885},{"id":"https://openalex.org/keywords/nonconvex-optimization","display_name":"non-convex optimization","score":0.9700000286102295},{"id":"https://openalex.org/keywords/l1-regularization","display_name":"L1 regularization","score":0.859000027179718},{"id":"https://openalex.org/keywords/interval-constraints","display_name":"interval constraints","score":0.9179999828338623},{"id":"https://openalex.org/keywords/sparse-neural-networks","display_name":"sparse neural networks","score":0.968999981880188},{"id":"https://openalex.org/keywords/binary-neural-networks","display_name":"binary neural networks","score":0.9980000257492065},{"id":"https://openalex.org/keywords/critical-points","display_name":"critical points","score":0.6380000114440918},{"id":"https://openalex.org/keywords/learning-rate","display_name":"learning rate","score":0.640999972820282}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6901811361312866},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6312800049781799},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5863889455795288},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5642827749252319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5526465177536011},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5167493224143982},{"id":"https://openalex.org/C63548660","wikidata":"https://www.wikidata.org/wiki/Q858223","display_name":"Limit point","level":2,"score":0.515884280204773},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.47440218925476074},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.47400912642478943},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4618571996688843},{"id":"https://openalex.org/C189237950","wikidata":"https://www.wikidata.org/wiki/Q2500758","display_name":"Stationary point","level":2,"score":0.4590934216976166},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.43709245324134827},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4262716770172119},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.4142211377620697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3965315818786621},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.36076635122299194},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32962414622306824},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"pmh:oai:orbilu.uni.lu:10993/45122","doi":null,"is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/45122","pdf_url":"http://orbilu.uni.lu/handle/10993/45122","source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"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":"International Conference on Learning Representations (ICLR) 2020 (2020); International Conference on Learning Representations (ICLR) 2020, 30-04-2020","raw_type":"http://purl.org/coar/resource_type/c_5794"},{"id":"pmh:oai:fraunhofer.de:N-590390","doi":null,"is_oa":true,"landing_page_url":"http://publica.fraunhofer.de/documents/N-590390.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"Fraunhofer ITWM","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/408129","doi":null,"is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/408129","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/501117","doi":null,"is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/501117","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/502303","doi":null,"is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/502303","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"},{"id":"mag:2995869484","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=HygpthEtvr","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":{"id":"pmh:oai:orbilu.uni.lu:10993/45122","doi":null,"is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/45122","pdf_url":"http://orbilu.uni.lu/handle/10993/45122","source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"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":"International Conference on Learning Representations (ICLR) 2020 (2020); International Conference on Learning Representations (ICLR) 2020, 30-04-2020","raw_type":"http://purl.org/coar/resource_type/c_5794"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2995869484.pdf","grobid_xml":"https://content.openalex.org/works/W2995869484.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1577245107","https://openalex.org/W1971942712","https://openalex.org/W2036749237","https://openalex.org/W2093545205","https://openalex.org/W2164278908","https://openalex.org/W2319920447","https://openalex.org/W2554592357","https://openalex.org/W2771655537","https://openalex.org/W2785523195","https://openalex.org/W2886837499","https://openalex.org/W2892684141","https://openalex.org/W2907225497","https://openalex.org/W2913535645","https://openalex.org/W2915589364","https://openalex.org/W2952139899","https://openalex.org/W2962958489","https://openalex.org/W2963114950","https://openalex.org/W2963446712","https://openalex.org/W2964121744","https://openalex.org/W4292363360"],"related_works":["https://openalex.org/W4282970603","https://openalex.org/W3127099038","https://openalex.org/W4200635661","https://openalex.org/W3126104326","https://openalex.org/W4296154337","https://openalex.org/W3042271683","https://openalex.org/W3167742250","https://openalex.org/W3185497386","https://openalex.org/W4303648922","https://openalex.org/W7096915593"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,79],"consider":[4],"the":[5,56,60,70,75,103],"problem":[6],"of":[7,55,77,102],"training":[8,24],"structured":[9],"neural":[10,96],"networks":[11,97],"(NN)":[12],"with":[13,49],"nonsmooth":[14,28],"regularization":[15,104],"(e.g.\u2113":[16],"1":[17],"-norm)":[18],"and":[19,32,73,106],"constraints":[20],"(e.g.interval":[21],"constraints).We":[22],"formulate":[23],"as":[25],"a":[26,34,65],"constrained":[27],"nonconvex":[29],"optimization":[30],"problem,":[31],"propose":[33],"convergent":[35],"proximal-type":[36],"stochastic":[37],"gradient":[38],"descent":[39],"(ProxSGD)":[40],"algorithm.We":[41],"show":[42,80],"that":[43],"under":[44],"properly":[45],"selected":[46],"learning":[47],"rates,":[48],"probability":[50],"1,":[51],"every":[52],"limit":[53],"point":[54],"sequence":[57],"generated":[58],"by":[59,81],"proposed":[61],"Prox-SGD":[62],"algorithm":[63],"is":[64],"stationary":[66],"point.Finally,":[67],"to":[68,90],"support":[69],"theoretical":[71],"analysis":[72],"demonstrate":[74],"flexibility":[76],"ProxSGD,":[78],"extensive":[82],"numerical":[83],"tests":[84],"how":[85],"ProxSGD":[86],"can":[87],"be":[88],"used":[89],"train":[91],"either":[92],"sparse":[93],"or":[94],"binary":[95],"through":[98],"an":[99],"adequate":[100],"selection":[101],"function":[105],"constraint":[107],"set.":[108]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2019-12-26T00:00:00"}