{"id":"https://openalex.org/W2991900752","doi":"https://doi.org/10.1109/allerton.2019.8919835","title":"An Elementary Approach to Convergence Guarantees of Optimization Algorithms for Deep Networks","display_name":"An Elementary Approach to Convergence Guarantees of Optimization Algorithms for Deep Networks","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2991900752","doi":"https://doi.org/10.1109/allerton.2019.8919835","mag":"2991900752"},"language":"en","primary_location":{"id":"doi:10.1109/allerton.2019.8919835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2019.8919835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","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/A5046132757","display_name":"Vincent Roulet","orcid":"https://orcid.org/0000-0001-6526-5235"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vincent Roulet","raw_affiliation_strings":["University of Washington,Department of Statistics,Seattle,USA","Department of Statistics, University of Washington, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Department of Statistics,Seattle,USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]},{"raw_affiliation_string":"Department of Statistics, University of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010613767","display_name":"Za\u00efd Harchaoui","orcid":"https://orcid.org/0000-0003-1186-1343"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zaid Harchaoui","raw_affiliation_strings":["University of Washington,Department of Statistics,Seattle,USA","Department of Statistics, University of Washington, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Department of Statistics,Seattle,USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]},{"raw_affiliation_string":"Department of Statistics, University of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"91"},"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.714866578578949},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.692489504814148},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5285545587539673},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5059108138084412},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49892139434814453},{"id":"https://openalex.org/keywords/exposition","display_name":"Exposition (narrative)","score":0.4940777122974396},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47203528881073},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.44295910000801086},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40640154480934143},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3572131395339966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3328794240951538},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19346338510513306}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.714866578578949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692489504814148},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5285545587539673},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5059108138084412},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49892139434814453},{"id":"https://openalex.org/C2776285698","wikidata":"https://www.wikidata.org/wiki/Q2642214","display_name":"Exposition (narrative)","level":2,"score":0.4940777122974396},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47203528881073},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.44295910000801086},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40640154480934143},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3572131395339966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3328794240951538},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19346338510513306},{"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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/allerton.2019.8919835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2019.8919835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","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":21,"referenced_works":["https://openalex.org/W182282593","https://openalex.org/W607505555","https://openalex.org/W1542886316","https://openalex.org/W1566309885","https://openalex.org/W1597009674","https://openalex.org/W1686810756","https://openalex.org/W2250539671","https://openalex.org/W2766736793","https://openalex.org/W2799148064","https://openalex.org/W2899771611","https://openalex.org/W2964113829","https://openalex.org/W2991900752","https://openalex.org/W4236362309","https://openalex.org/W4243599615","https://openalex.org/W4288259560","https://openalex.org/W6607393373","https://openalex.org/W6635935089","https://openalex.org/W6637373629","https://openalex.org/W6682610290","https://openalex.org/W6685350579","https://openalex.org/W6763331544"],"related_works":["https://openalex.org/W2356114564","https://openalex.org/W2350151408","https://openalex.org/W2380661758","https://openalex.org/W3005974700","https://openalex.org/W3006355877","https://openalex.org/W3165905718","https://openalex.org/W3006351327","https://openalex.org/W2327984862","https://openalex.org/W1515987003","https://openalex.org/W2371230950"],"abstract_inverted_index":{"We":[0,44],"present":[1],"an":[2],"approach":[3],"to":[4,34,49,64,84],"obtain":[5],"convergence":[6,21,57],"guarantees":[7],"of":[8,30,37,59,71],"optimization":[9,31,61],"algorithms":[10,62],"for":[11],"deep":[12,38,66,79],"networks":[13,39,80],"based":[14],"on":[15],"elementary":[16],"arguments":[17],"and":[18,27,74],"computations.":[19],"The":[20],"analysis":[22],"revolves":[23],"around":[24],"the":[25,35,51,56,82,86],"analytical":[26],"computational":[28],"structures":[29],"oracles":[32],"central":[33],"implementation":[36],"in":[40,77],"machine":[41],"learning":[42],"software.":[43],"provide":[45],"a":[46],"systematic":[47],"way":[48],"compute":[50],"smoothness":[52],"constants":[53],"that":[54],"govern":[55],"behavior":[58],"first-order":[60],"used":[63],"train":[65],"networks.":[67],"A":[68],"diverse":[69],"set":[70],"example":[72],"components":[73],"architectures":[75],"arising":[76],"modern":[78],"intersperse":[81],"exposition":[83],"illustrate":[85],"approach.":[87]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}