{"id":"https://openalex.org/W4393380212","doi":"https://doi.org/10.1109/ieeeconf59524.2023.10476957","title":"Local Convergence of Gradient Descent-Ascent for Training Generative Adversarial Networks","display_name":"Local Convergence of Gradient Descent-Ascent for Training Generative Adversarial Networks","publication_year":2023,"publication_date":"2023-10-29","ids":{"openalex":"https://openalex.org/W4393380212","doi":"https://doi.org/10.1109/ieeeconf59524.2023.10476957"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf59524.2023.10476957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf59524.2023.10476957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"type":"article","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/A5027375284","display_name":"Evan Becker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Evan Becker","raw_affiliation_strings":["CS, UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CS, UCLA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083224560","display_name":"Parthe Pandit","orcid":"https://orcid.org/0000-0002-2524-8817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Parthe Pandit","raw_affiliation_strings":["HDSI, UCSD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HDSI, UCSD","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000099903","display_name":"Sundeep Rangan","orcid":"https://orcid.org/0000-0002-0925-8169"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sundeep Rangan","raw_affiliation_strings":["ECE, NYU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE, NYU","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073129946","display_name":"Alyson K. Fletcher","orcid":"https://orcid.org/0000-0002-3756-6580"},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alyson K. Fletcher","raw_affiliation_strings":["Statistics, UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Statistics, UCLA","institution_ids":["https://openalex.org/I2799798094"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2246,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55014398,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"892","last_page":"896"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9739000201225281,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9739000201225281,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9560999870300293,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9451000094413757,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.7402856349945068},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7133619785308838},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.709123969078064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6361023187637329},{"id":"https://openalex.org/keywords/descent","display_name":"Descent (aeronautics)","score":0.6287781000137329},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.612233579158783},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5334594249725342},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4977419674396515},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.48225027322769165},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4142466187477112},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3362814784049988},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23037365078926086},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.12095731496810913},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09743472933769226},{"id":"https://openalex.org/keywords/aerospace-engineering","display_name":"Aerospace engineering","score":0.05202263593673706}],"concepts":[{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.7402856349945068},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7133619785308838},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.709123969078064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6361023187637329},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.6287781000137329},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.612233579158783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5334594249725342},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4977419674396515},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.48225027322769165},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4142466187477112},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3362814784049988},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23037365078926086},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12095731496810913},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09743472933769226},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.05202263593673706},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf59524.2023.10476957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf59524.2023.10476957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2419501139","https://openalex.org/W2785678896","https://openalex.org/W2792263949","https://openalex.org/W2797315706","https://openalex.org/W2809090039","https://openalex.org/W2963373786","https://openalex.org/W2964126461","https://openalex.org/W2964201867","https://openalex.org/W3096831136","https://openalex.org/W4240805545","https://openalex.org/W4292953615","https://openalex.org/W4302585512","https://openalex.org/W4376653751","https://openalex.org/W6688325169","https://openalex.org/W6717434760","https://openalex.org/W6718379498","https://openalex.org/W6745560452","https://openalex.org/W6748582592","https://openalex.org/W6752495264","https://openalex.org/W6785092453","https://openalex.org/W6842481150","https://openalex.org/W6852788042"],"related_works":["https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4362706668","https://openalex.org/W4231621013","https://openalex.org/W2015288657","https://openalex.org/W3171021120","https://openalex.org/W3008318776","https://openalex.org/W2041416246"],"abstract_inverted_index":{"Generative":[0],"Adversarial":[1],"Networks":[2],"(GANs)":[3],"are":[4],"a":[5,24,30,59,62,71,74],"popular":[6],"formulation":[7],"to":[8,38,43],"train":[9],"generative":[10],"models":[11],"for":[12,20,57],"complex":[13],"high":[14],"dimensional":[15],"data.":[16],"The":[17],"standard":[18],"method":[19],"training":[21,58],"GANs":[22],"involves":[23],"gradient":[25],"descent-ascent":[26],"(GDA)":[27],"procedure":[28,35],"on":[29,70,109,147],"minimax":[31],"optimization":[32],"problem.":[33],"This":[34,65],"is":[36,68,145],"hard":[37],"analyze":[39],"in":[40],"general":[41],"due":[42],"the":[44,48,52,80,95,98,103,106,110,124],"nonlinear":[45,75],"nature":[46],"of":[47,55,73,97,105,114],"dynamics.":[49],"We":[50,130],"study":[51],"local":[53,111],"dynamics":[54],"GDA":[56,81],"GAN":[60],"with":[61,142],"kernel-based":[63],"discriminator.":[64],"convergence":[66,112],"analysis":[67,92],"based":[69],"linearization":[72],"dynamical":[76],"system":[77,125],"that":[78,121,135],"describes":[79],"iterations,":[82],"under":[83],"an":[84],"isolated":[85],"points":[86],"model":[87],"assumption":[88],"from":[89],"[2].":[90],"Our":[91],"brings":[93],"out":[94],"effect":[96],"learning":[99],"rates,":[100],"regularization,":[101],"and":[102],"bandwidth":[104],"kernel":[107],"discriminator,":[108],"rate":[113],"GDA.":[115],"Importantly,":[116],"we":[117],"show":[118],"phase":[119],"transitions":[120],"indicate":[122],"when":[123],"converges,":[126],"oscillates,":[127],"or":[128],"diverges.":[129],"also":[131],"provide":[132],"numerical":[133],"simulations":[134],"verify":[136],"our":[137],"claims.":[138],"A":[139],"full":[140],"version":[141],"complete":[143],"proofs":[144],"available":[146],"arXiv":[148],"[3].":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}