{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:20:14Z","timestamp":1760710814169,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"GN A\/S"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3133762","type":"journal-article","created":{"date-parts":[[2021,12,7]],"date-time":"2021-12-07T20:36:03Z","timestamp":1638909363000},"page":"165366-165384","source":"Crossref","is-referenced-by-count":3,"title":["Convergence and Optimality Analysis of Low-Dimensional Generative Adversarial Networks Using Error Function Integrals"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5241-2301","authenticated-orcid":false,"given":"Graham W.","family":"Pulford","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kirill","family":"Kondrashov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Training generative adversarial networks by solving ordinary differential equations","author":"qin","year":"2020","journal-title":"arXiv 2010 15040"},{"journal-title":"Probability random variables and stochastic processes","year":"1991","author":"papoulis","key":"ref38"},{"key":"ref33","article-title":"Convergence and sample complexity of SGD in GANs","author":"kontonis","year":"2020","journal-title":"arXiv 2012 00732"},{"key":"ref32","first-page":"1","article-title":"Characterizing GAN convergence through proximal duality gap","author":"sidheekh","year":"2021","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref31","article-title":"GANs may have no Nash equilibria","author":"farnia","year":"2020","journal-title":"arXiv 2002 09124"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2924428"},{"key":"ref37","article-title":"NIPS 2016 tutorial: Generative adversarial networks","author":"goodfellow","year":"2017","journal-title":"arXiv 1701 00160"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2864500"},{"key":"ref35","article-title":"Effect of input noise dimension in GANs","author":"manisha","year":"2020","journal-title":"arXiv 2004 06882"},{"key":"ref34","first-page":"1","article-title":"Towards a better global loss landscape of GANs","author":"sun","year":"2020","journal-title":"Proc 34th Conf Neural Inf Process Syst"},{"key":"ref28","first-page":"3481","article-title":"Which training methods for GANs do actually converge","author":"mescheder","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","first-page":"1","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","author":"heusel","year":"2017","journal-title":"Proc Ann Conf Neural Info Proc Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4360-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2018.8482813"},{"key":"ref1","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01295"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-4-431-55978-8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01029"},{"key":"ref24","first-page":"1","article-title":"Towards principled methods for training generative adversarial networks","author":"arjovsky","year":"2017","journal-title":"Proc 5th Int Conf Learn Represent"},{"key":"ref23","first-page":"1","article-title":"Center manifold analysis of plateau phenomena caused by degeneration of three-layer perceptron","volume":"32","author":"tsutsui","year":"2018","journal-title":"Neural Comput"},{"key":"ref26","first-page":"5591","article-title":"Gradient descent GAN optimization is locally stable","author":"nagarajan","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3089285"},{"journal-title":"Animation of 2-D Parameter Trajectory on a Generative Adversarial Network (GAN) Cost Surface","year":"2021","author":"pulford","key":"ref50"},{"journal-title":"Github Repository for 1-D Least Squares Generative Adversarial Networks","year":"2021","author":"kondrashov","key":"ref51"},{"key":"ref55","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"arXiv 1312 6114"},{"key":"ref54","article-title":"Gradient descent can take exponential time to escape saddle points","author":"du","year":"2017","journal-title":"arXiv 1705 10412"},{"key":"ref53","article-title":"Global optimization-based dimer method for finding saddle points","author":"yu","year":"2019","journal-title":"arXiv 1910 05703"},{"key":"ref52","article-title":"Troubling trends in machine learning scholarship","author":"lipton","year":"2018","journal-title":"arXiv 1807 03341"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3130191"},{"key":"ref40","article-title":"From optimal transport to generative modeling—The VEGAN cookbook","author":"bousquet","year":"2017","journal-title":"arXiv 1705 07642"},{"key":"ref11","first-page":"1","article-title":"Evaluation of mode collapse in generative adversarial networks","author":"lala","year":"2018","journal-title":"Proc IEEE Conf High Perf Extreme Comput"},{"key":"ref12","article-title":"Wasserstein GAN","author":"arjovsky","year":"2017","journal-title":"arXiv 1701 07875"},{"key":"ref13","article-title":"A review of generative adversarial networks (GANs) and its applications in a wide variety of disciplines–from medical to remote sensing","author":"dash","year":"2021","journal-title":"arXiv 2110 01442"},{"key":"ref14","article-title":"Generative adversarial networks (GANs): Challenges, solutions, and future directions","author":"saxena","year":"2020","journal-title":"arXiv 2005 00065"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2895748"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2021.3068842"},{"key":"ref17","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref18","article-title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","author":"saxe","year":"2014","journal-title":"arXiv 1312 6120"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00091"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510583"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CAC.2018.8623645"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2872043"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref8","article-title":"Improved techniques for training GANs","author":"salimans","year":"2016","journal-title":"arXiv 1606 03498"},{"journal-title":"Animation of 2-D Parameter Trajectory on a Generative Adversarial Network (GAN) Cost Surface","year":"2021","author":"pulford","key":"ref49"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2905015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2886814"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"journal-title":"Pattern Recognition and Machine Learning","year":"2009","author":"bishop","key":"ref45"},{"key":"ref48","first-page":"1","article-title":"Step size matters in deep learning","author":"nar","year":"2018","journal-title":"Proc Conf Neural Inf Process Sys"},{"key":"ref47","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref42","first-page":"1","article-title":"A table of integrals of the error functions","volume":"73b","author":"edward","year":"1968","journal-title":"J Res Na Bur Stand"},{"journal-title":"Table of Integrals Series and Products","year":"2007","author":"gradshteyn","key":"ref41"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1201\/9780367809232"},{"journal-title":"Integrals and Series","year":"1986","author":"prudnikov","key":"ref43"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09641798.pdf?arnumber=9641798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,28]],"date-time":"2022-03-28T21:23:10Z","timestamp":1648502590000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9641798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3133762","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}