{"id":"https://openalex.org/W2981407587","doi":"https://doi.org/10.1007/s10994-019-05839-6","title":"Gradient descent optimizes over-parameterized deep ReLU networks","display_name":"Gradient descent optimizes over-parameterized deep ReLU networks","publication_year":2019,"publication_date":"2019-10-23","ids":{"openalex":"https://openalex.org/W2981407587","doi":"https://doi.org/10.1007/s10994-019-05839-6","mag":"2981407587"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-019-05839-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05839-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05839-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05839-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085848346","display_name":"Difan Zou","orcid":"https://orcid.org/0000-0002-6544-2593"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Difan Zou","raw_affiliation_strings":["Department of Computer Science, University of California, Los Angeles, CA, 90095, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Los Angeles, CA, 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101989491","display_name":"Yuan Cao","orcid":"https://orcid.org/0000-0002-2495-4701"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Cao","raw_affiliation_strings":["Department of Computer Science, University of California, Los Angeles, CA, 90095, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Los Angeles, CA, 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080386620","display_name":"Dongruo Zhou","orcid":"https://orcid.org/0009-0005-3889-071X"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongruo Zhou","raw_affiliation_strings":["Department of Computer Science, University of California, Los Angeles, CA, 90095, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Los Angeles, CA, 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051448391","display_name":"Quanquan Gu","orcid":"https://orcid.org/0000-0001-9830-793X"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Quanquan Gu","raw_affiliation_strings":["Department of Computer Science, University of California, Los Angeles, CA, 90095, USA"],"raw_orcid":"https://orcid.org/0000-0001-9830-793X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Los Angeles, CA, 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051448391"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":15.4627,"has_fulltext":true,"cited_by_count":226,"citation_normalized_percentile":{"value":0.9944224,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"109","issue":"3","first_page":"467","last_page":"492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9973999857902527,"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/initialization","display_name":"Initialization","score":0.7787349224090576},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.7680342197418213},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.7623663544654846},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6487593650817871},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6105652451515198},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.6066381931304932},{"id":"https://openalex.org/keywords/iterated-function","display_name":"Iterated function","score":0.48987361788749695},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44563156366348267},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4296572208404541},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42422959208488464},{"id":"https://openalex.org/keywords/activation-function","display_name":"Activation function","score":0.4173431396484375},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4072212874889374},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.37139999866485596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31711721420288086},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.17355138063430786}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7787349224090576},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.7680342197418213},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.7623663544654846},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6487593650817871},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6105652451515198},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.6066381931304932},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.48987361788749695},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44563156366348267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4296572208404541},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42422959208488464},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.4173431396484375},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4072212874889374},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.37139999866485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31711721420288086},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.17355138063430786},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-019-05839-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05839-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05839-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-019-05839-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05839-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05839-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3722066678","display_name":"BIGDATA: F: Collaborative Research: Taming Big Networks via Embedding","funder_award_id":"1855099","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5325791252","display_name":"III: Small: Collaborative Research: High-Dimensional Machine Learning Methods for Personalized Cancer Genomics","funder_award_id":"1903202","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6024092204","display_name":"CAREER:  Scaling Up Knowledge Discovery in High-Dimensional Data Via Nonconvex Statistical Optimization","funder_award_id":"1906169","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2981407587.pdf","grobid_xml":"https://content.openalex.org/works/W2981407587.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1988115241","https://openalex.org/W2064675550","https://openalex.org/W2112796928","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2257979135","https://openalex.org/W2528305538","https://openalex.org/W2810898455","https://openalex.org/W2886685759","https://openalex.org/W2963446085","https://openalex.org/W2965497096","https://openalex.org/W3118608800","https://openalex.org/W6713348437","https://openalex.org/W6751318643"],"related_works":["https://openalex.org/W3016512554","https://openalex.org/W4287825651","https://openalex.org/W2425229278","https://openalex.org/W4226299596","https://openalex.org/W4287868543","https://openalex.org/W4309434778","https://openalex.org/W4221140299","https://openalex.org/W3214759249","https://openalex.org/W4210308499","https://openalex.org/W4283773090"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":33},{"year":2022,"cited_by_count":40},{"year":2021,"cited_by_count":65},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}