{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:35:36Z","timestamp":1775230536632,"version":"3.50.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science Foundation","award":["CIF-1901243"],"award-info":[{"award-number":["CIF-1901243"]}]},{"name":"National Science Foundation","award":["CIF-1815361"],"award-info":[{"award-number":["CIF-1815361"]}]},{"name":"National Science Foundation","award":["CIF-2007688"],"award-info":[{"award-number":["CIF-2007688"]}]},{"name":"National Science Foundation","award":["DMS-2134256"],"award-info":[{"award-number":["DMS-2134256"]}]},{"name":"National Science Foundation","award":["SCH-2205080"],"award-info":[{"award-number":["SCH-2205080"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Areas Inf. Theory"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/jsait.2024.3415670","type":"journal-article","created":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T17:31:33Z","timestamp":1718818293000},"page":"534-553","source":"Crossref","is-referenced-by-count":17,"title":["Addressing GAN Training Instabilities via Tunable Classification Losses"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8439-5668","authenticated-orcid":false,"given":"Monica","family":"Welfert","sequence":"first","affiliation":[{"name":"School of Electrical, Computer, and Energy Engineering, Arizona State University, Tempe, AZ, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6031-4114","authenticated-orcid":false,"given":"Gowtham R.","family":"Kurri","sequence":"additional","affiliation":[{"name":"School of Electrical, Computer, and Energy Engineering, Arizona State University, Tempe, AZ, USA"}]},{"given":"Kyle","family":"Otstot","sequence":"additional","affiliation":[{"name":"School of Electrical, Computer, and Energy Engineering, Arizona State University, Tempe, AZ, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8122-5444","authenticated-orcid":false,"given":"Lalitha","family":"Sankar","sequence":"additional","affiliation":[{"name":"School of Electrical, Computer, and Energy Engineering, Arizona State University, Tempe, AZ, USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/18.61115"},{"key":"ref3","first-page":"1","article-title":"f-GAN: Training generative neural samplers using variational divergence minimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Nowozin"},{"key":"ref4","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","volume":"70","author":"Arjovsky"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1214\/12-EJS722"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3714011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ITW48936.2021.9611499"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849796"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2022.3169440"},{"issue":"4","key":"ref10","first-page":"389","article-title":"On a class of perimeter-type distances of probability distributions","volume":"32","author":"\u00d6sterreicher","year":"1996","journal-title":"Kybernetika"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.881731"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT50566.2022.9834890"},{"key":"ref13","article-title":"Towards principled methods for training generative adversarial networks","author":"Arjovsky","year":"2017","journal-title":"arXiv:1701.04862"},{"key":"ref14","article-title":"Stabilizing generative adversarial networks: A survey","author":"Wiatrak","year":"2019","journal-title":"arXiv:1910.00927"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01416"},{"key":"ref17","article-title":"Improved generator objectives for GANs","author":"Poole","year":"2016","journal-title":"arXiv:1612.02780"},{"key":"ref18","first-page":"1","article-title":"(\u03b1D,\u03b1G)-GANs: Addressing GAN training instabilities via dual objectives","volume-title":"Proc. IEEE ISIT","author":"Welfert"},{"key":"ref19","first-page":"224","article-title":"Generalization and equilibrium in generative adversarial nets (GANs)","volume-title":"Proc. 34th ICML","volume":"70","author":"Arora"},{"key":"ref20","first-page":"1","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Salimans"},{"key":"ref21","first-page":"1","article-title":"Bias and generalization in deep generative models: An empirical study","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Zhao"},{"key":"ref22","article-title":"How (not) to train your generative model: Scheduled sampling, likelihood, adversary?","author":"Husz\u00e1r","year":"2015","journal-title":"arXiv:1511.05101"},{"key":"ref23","first-page":"1","article-title":"MMD GAN: Towards deeper understanding of moment matching network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Li"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.10717"},{"key":"ref25","first-page":"1","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Gulrajani"},{"key":"ref26","first-page":"1","article-title":"Fisher GAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Mroueh"},{"key":"ref27","first-page":"2527","article-title":"McGan: Mean and covariance feature matching GAN","volume-title":"Proc. 34th ICML","volume":"70","author":"Mroueh"},{"key":"ref28","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015","journal-title":"arXiv:1511.06434"},{"key":"ref29","article-title":"Adversarial feature learning","author":"Donahue","year":"2016","journal-title":"arXiv:1605.09782"},{"key":"ref30","article-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"Karras","year":"2017","journal-title":"arXiv:1710.10196"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref32","article-title":"Training generative neural networks via maximum mean discrepancy optimization","author":"Dziugaite","year":"2015","journal-title":"arXiv:1505.03906"},{"key":"ref33","first-page":"1718","article-title":"Generative moment matching networks","volume-title":"Proc. 32nd ICML","volume":"37","author":"Li"},{"key":"ref34","article-title":"Sobolev GAN","author":"Mroueh","year":"2017","journal-title":"arXiv:1711.04894"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2983071"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT45174.2021.9517791"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01172"},{"key":"ref38","article-title":"A unifying generator loss function for generative adversarial networks","author":"Veiner","year":"2023","journal-title":"arXiv:2308.07233"},{"key":"ref39","article-title":"Adversarial training should be cast as a non-zero-sum game","author":"Robey","year":"2023","journal-title":"arXiv:2306.11035"},{"key":"ref40","first-page":"1","article-title":"On the discrimination-Generalization tradeoff in GANs","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhou"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2021.3053234"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2068870"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1214\/08-AOS595"},{"key":"ref44","first-page":"229","article-title":"Information-type measures of difference of probability distributions and indirect observation","volume":"2","author":"Csisz\u00e1r","year":"1967","journal-title":"Studia Scientiarum Mathematicarum Hungarica"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1966.tb00626.x"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71050-9"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(71)90065-9"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2018.8437307"},{"key":"ref49","first-page":"2387","article-title":"Composite binary losses","volume":"11","author":"Reid","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1198\/016214505000000907"},{"key":"ref51","volume-title":"Convex Statistical Distances","author":"Liese","year":"1987"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133079"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/BF02517812"},{"key":"ref54","article-title":"Tighter variational representations of f-divergences via restriction to probability measures","author":"Ruderman","year":"2012","journal-title":"arXiv:1206.4664"},{"key":"ref55","first-page":"531","article-title":"MINE: Mutual information neural estimation","volume-title":"Proc. 35th ICML","volume":"80","author":"Belghazi"},{"key":"ref56","article-title":"Properties of f-divergences and f-GAN training","author":"Shannon","year":"2020","journal-title":"arXiv:2009.00757"},{"key":"ref57","first-page":"1","article-title":"Approximation and convergence properties of generative adversarial learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Liu"},{"issue":"2","key":"ref58","first-page":"191","article-title":"A note on f-divergences","volume":"24","author":"Feldman","year":"1989","journal-title":"Studia Scientiarum Mathematicarum Hungarica"},{"key":"ref59","first-page":"1","article-title":"Minimax estimation of neural net distance","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Ji"},{"key":"ref60","first-page":"1376","article-title":"Norm-based capacity control in neural networks","volume-title":"Proc. Conf. Learn. Theory","author":"Neyshabur"},{"key":"ref61","first-page":"1","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Salimans"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaz007"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3569928"},{"key":"ref65","first-page":"1","article-title":"VEEGAN: Reducing mode collapse in GANs using implicit variational learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Srivastava"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref67","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015","journal-title":"arXiv:1506.03365"},{"key":"ref68","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref69","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref70","first-page":"11691","article-title":"Outlier-robust optimal transport: Duality, structure, and statistical analysis","volume-title":"Proc. 25th Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"Nietert"}],"container-title":["IEEE Journal on Selected Areas in Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8700143\/10461668\/10565846-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8700143\/10461668\/10565846.pdf?arnumber=10565846","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T21:04:05Z","timestamp":1736543045000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10565846\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/jsait.2024.3415670","relation":{},"ISSN":["2641-8770"],"issn-type":[{"value":"2641-8770","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}