{"id":"https://openalex.org/W3214073196","doi":"https://doi.org/10.1162/neco_a_01457","title":"Nonconvex Sparse Regularization for Deep Neural Networks and Its Optimality","display_name":"Nonconvex Sparse Regularization for Deep Neural Networks and Its Optimality","publication_year":2021,"publication_date":"2021-11-11","ids":{"openalex":"https://openalex.org/W3214073196","doi":"https://doi.org/10.1162/neco_a_01457","mag":"3214073196","pmid":"https://pubmed.ncbi.nlm.nih.gov/34758482"},"language":"en","primary_location":{"id":"doi:10.1162/neco_a_01457","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_01457","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718","https://openalex.org/P4310316440"],"host_organization_lineage_names":["The MIT Press","Massachusetts Institute of Technology"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","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/A5022240133","display_name":"Ilsang Ohn","orcid":"https://orcid.org/0000-0003-3953-5953"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ilsang Ohn","raw_affiliation_strings":["Department of Applied and Computational Mathematics and Statistics, University of Notre Dame, Notre Dame, IN 46556, U.S.A. iohn@nd.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied and Computational Mathematics and Statistics, University of Notre Dame, Notre Dame, IN 46556, U.S.A. iohn@nd.edu","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011264910","display_name":"Yongdai Kim","orcid":"https://orcid.org/0000-0002-9434-5645"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yongdai Kim","raw_affiliation_strings":["Department of Statistics, Seoul National University, Seoul 08826, Republic of Korea ydkim0903@gmail.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Seoul National University, Seoul 08826, Republic of Korea ydkim0903@gmail.com","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011264910","https://openalex.org/A5022240133"],"corresponding_institution_ids":["https://openalex.org/I107639228","https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":1.5193,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.79741501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"34","issue":"2","first_page":"476","last_page":"517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998999834060669,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9894000291824341,"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/minimax","display_name":"Minimax","score":0.6512240171432495},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6350023150444031},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5806736946105957},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5737593173980713},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5505823493003845},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4989161491394043},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4975869953632355},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.4869755208492279},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.47008800506591797},{"id":"https://openalex.org/keywords/empirical-risk-minimization","display_name":"Empirical risk minimization","score":0.46232345700263977},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4408136308193207},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.437350332736969},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.41498637199401855},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3534133732318878},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3082233965396881}],"concepts":[{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.6512240171432495},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6350023150444031},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5806736946105957},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5737593173980713},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5505823493003845},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4989161491394043},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4975869953632355},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4869755208492279},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47008800506591797},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.46232345700263977},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4408136308193207},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.437350332736969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41498637199401855},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3534133732318878},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3082233965396881},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1162/neco_a_01457","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_01457","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718","https://openalex.org/P4310316440"],"host_organization_lineage_names":["The MIT Press","Massachusetts Institute of Technology"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:34758482","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34758482","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":"Neural computation","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1935978687","https://openalex.org/W1965125844","https://openalex.org/W2009689404","https://openalex.org/W2015052585","https://openalex.org/W2050127944","https://openalex.org/W2065274576","https://openalex.org/W2074682976","https://openalex.org/W2146502635","https://openalex.org/W2156387975","https://openalex.org/W2162430620","https://openalex.org/W2166765763","https://openalex.org/W2166956514","https://openalex.org/W2528305538","https://openalex.org/W2559655401","https://openalex.org/W2766574708","https://openalex.org/W2895992958","https://openalex.org/W2899595014","https://openalex.org/W2912099989","https://openalex.org/W2946302218","https://openalex.org/W2949491641","https://openalex.org/W2949935872","https://openalex.org/W2951338616","https://openalex.org/W2962965870","https://openalex.org/W2963146412","https://openalex.org/W2963264710","https://openalex.org/W2963285578","https://openalex.org/W2963828549","https://openalex.org/W2968917279","https://openalex.org/W3098306969","https://openalex.org/W3101333873","https://openalex.org/W3101636142","https://openalex.org/W3102333781","https://openalex.org/W3102511045","https://openalex.org/W3130671418","https://openalex.org/W3158239814","https://openalex.org/W3201938571","https://openalex.org/W4212774754","https://openalex.org/W4244393449","https://openalex.org/W4320930577","https://openalex.org/W6630000285","https://openalex.org/W6640289440","https://openalex.org/W6681435938","https://openalex.org/W6682889407","https://openalex.org/W6683637934","https://openalex.org/W6684416548","https://openalex.org/W6745499552","https://openalex.org/W6748059092","https://openalex.org/W6755463368","https://openalex.org/W6755984802","https://openalex.org/W6785335769"],"related_works":["https://openalex.org/W2016058626","https://openalex.org/W2474724840","https://openalex.org/W2895916002","https://openalex.org/W3110702597","https://openalex.org/W1530911128","https://openalex.org/W1814049089","https://openalex.org/W1570812264","https://openalex.org/W2073713056","https://openalex.org/W2522078129","https://openalex.org/W3172664294"],"abstract_inverted_index":{"Recent":[0],"theoretical":[1],"studies":[2],"proved":[3],"that":[4,74,110,134],"deep":[5],"neural":[6],"network":[7],"(DNN)":[8],"estimators":[9],"obtained":[10],"by":[11],"minimizing":[12],"empirical":[13],"risk":[14,91],"with":[15],"a":[16,66],"certain":[17,36],"sparsity":[18,32,59,81],"constraint":[19,33],"can":[20,114],"attain":[21,116],"optimal":[22],"convergence":[23,100,118],"rates":[24,101,119],"for":[25,71,88,102,120],"regression":[26,123],"and":[27,98],"classification":[28],"problems.":[29,124],"However,":[30],"the":[31,39,54,58,76,80,89,93,111,136,140],"requires":[34],"knowing":[35],"properties":[37],"of":[38,57,92,139],"true":[40],"model,":[41],"which":[42],"are":[43],"not":[44],"available":[45],"in":[46,79],"practice.":[47],"Moreover,":[48],"computation":[49],"is":[50],"difficult":[51],"due":[52],"to":[53],"discrete":[55],"nature":[56],"constraint.":[60,82],"In":[61,106],"this":[62],"letter,":[63],"we":[64,108,127],"propose":[65],"novel":[67],"penalized":[68],"estimation":[69],"method":[70],"sparse":[72],"DNNs":[73],"resolves":[75],"problems":[77],"existing":[78],"We":[83],"establish":[84],"an":[85,129],"oracle":[86],"inequality":[87],"excess":[90],"proposed":[94],"sparse-penalized":[95,112],"DNN":[96],"estimator":[97,113],"derive":[99],"several":[103],"learning":[104],"tasks.":[105],"particular,":[107],"prove":[109],"adaptively":[115],"minimax":[117],"various":[121],"nonparametric":[122],"For":[125],"computation,":[126],"develop":[128],"efficient":[130],"gradient-based":[131],"optimization":[132],"algorithm":[133],"guarantees":[135],"monotonic":[137],"reduction":[138],"objective":[141],"function.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}