{"id":"https://openalex.org/W3118672966","doi":"https://doi.org/10.1109/cdc42340.2020.9304386","title":"The Role of Regularization in Overparameterized Neural Networks","display_name":"The Role of Regularization in Overparameterized Neural Networks","publication_year":2020,"publication_date":"2020-12-14","ids":{"openalex":"https://openalex.org/W3118672966","doi":"https://doi.org/10.1109/cdc42340.2020.9304386","mag":"3118672966"},"language":"en","primary_location":{"id":"doi:10.1109/cdc42340.2020.9304386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9304386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5039591285","display_name":"Siddhartha Satpathi","orcid":"https://orcid.org/0000-0001-5359-7793"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhartha Satpathi","raw_affiliation_strings":["University of Illinois at Urbana Champaign,Department of Electrical and Computer Engineering and the Coordinated Science Lab,Champaign,IL,USA,61820"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign,Department of Electrical and Computer Engineering and the Coordinated Science Lab,Champaign,IL,USA,61820","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101600794","display_name":"Harsh Gupta","orcid":"https://orcid.org/0000-0002-7845-5078"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harsh Gupta","raw_affiliation_strings":["University of Illinois at Urbana Champaign,Department of Electrical and Computer Engineering and the Coordinated Science Lab,Champaign,IL,USA,61820"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign,Department of Electrical and Computer Engineering and the Coordinated Science Lab,Champaign,IL,USA,61820","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083787469","display_name":"Shiyu Liang","orcid":"https://orcid.org/0009-0003-2917-2033"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyu Liang","raw_affiliation_strings":["University of Illinois at Urbana Champaign,Department of Electrical and Computer Engineering and the Coordinated Science Lab,Champaign,IL,USA,61820"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign,Department of Electrical and Computer Engineering and the Coordinated Science Lab,Champaign,IL,USA,61820","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078518595","display_name":"R. Srikant","orcid":"https://orcid.org/0000-0003-1483-5204"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R Srikant","raw_affiliation_strings":["University of Illinois at Urbana Champaign,Department of Electrical and Computer Engineering and the Coordinated Science Lab,Champaign,IL,USA,61820"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign,Department of Electrical and Computer Engineering and the Coordinated Science Lab,Champaign,IL,USA,61820","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4683","last_page":"4688"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T12676","display_name":"Machine Learning and ELM","score":0.9991000294685364,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9990000128746033,"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/regularization","display_name":"Regularization (linguistics)","score":0.8134960532188416},{"id":"https://openalex.org/keywords/ode","display_name":"Ode","score":0.7683193683624268},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7208237051963806},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.7025854587554932},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6167814135551453},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6123381853103638},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.47772976756095886},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43116357922554016},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4275768995285034},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4235861003398895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4085094928741455},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3354494869709015},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.13496795296669006}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.8134960532188416},{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.7683193683624268},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7208237051963806},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.7025854587554932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6167814135551453},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6123381853103638},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.47772976756095886},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43116357922554016},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4275768995285034},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4235861003398895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4085094928741455},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3354494869709015},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.13496795296669006}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc42340.2020.9304386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9304386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1944672","https://openalex.org/W1533861849","https://openalex.org/W1677182931","https://openalex.org/W2144513243","https://openalex.org/W2777662428","https://openalex.org/W2789350251","https://openalex.org/W2799160179","https://openalex.org/W2809090039","https://openalex.org/W2899748887","https://openalex.org/W2900103278","https://openalex.org/W2900959181","https://openalex.org/W2914811257","https://openalex.org/W2945554113","https://openalex.org/W2950987997","https://openalex.org/W2952204734","https://openalex.org/W2963239103","https://openalex.org/W2975935587","https://openalex.org/W2995097486","https://openalex.org/W2996168800","https://openalex.org/W2996822312","https://openalex.org/W2997793548","https://openalex.org/W3001454063","https://openalex.org/W3118672966","https://openalex.org/W3122402965","https://openalex.org/W3159649695","https://openalex.org/W4289293816","https://openalex.org/W4289436733","https://openalex.org/W6631943919","https://openalex.org/W6681151457","https://openalex.org/W6747381837","https://openalex.org/W6748318183","https://openalex.org/W6750339013","https://openalex.org/W6752495264","https://openalex.org/W6755150206","https://openalex.org/W6756137178","https://openalex.org/W6758902322","https://openalex.org/W6759511767","https://openalex.org/W6762441359","https://openalex.org/W6763681727","https://openalex.org/W6764442487","https://openalex.org/W6768178264","https://openalex.org/W6768332837","https://openalex.org/W6770495777","https://openalex.org/W6772095464","https://openalex.org/W6773606474"],"related_works":["https://openalex.org/W2115605526","https://openalex.org/W3093883775","https://openalex.org/W1539246760","https://openalex.org/W2786746258","https://openalex.org/W4225893763","https://openalex.org/W2788727425","https://openalex.org/W2405196115","https://openalex.org/W2104893957","https://openalex.org/W4402471162","https://openalex.org/W2971074373"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"consider":[4],"gradient":[5],"descent":[6],"on":[7],"a":[8],"regularized":[9],"loss":[10],"function":[11],"for":[12],"training":[13,39],"an":[14,23],"overparametrized":[15],"neural":[16],"network.":[17],"We":[18],"model":[19],"the":[20,35],"algorithm":[21],"as":[22],"ODE":[24],"and":[25,29,40],"show":[26],"how":[27],"overparameterization":[28],"regularization":[30],"work":[31],"together":[32],"to":[33],"provide":[34],"right":[36],"tradeoff":[37],"between":[38],"generalization":[41],"errors.":[42]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}