{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:20:22Z","timestamp":1773415222679,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"NSF","doi-asserted-by":"publisher","award":["RI-1929955"],"award-info":[{"award-number":["RI-1929955"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"NSF","doi-asserted-by":"publisher","award":["CCF-1927712"],"award-info":[{"award-number":["CCF-1927712"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004830","name":"Siemens AG","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004830","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Extreme Science and Engineering Discovery Environment"},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["OCI-1053575"],"award-info":[{"award-number":["OCI-1053575"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Bridges system"},{"name":"NSF, at the Pittsburgh Supercomputing Center","award":["ACI-1445606"],"award-info":[{"award-number":["ACI-1445606"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Areas Inf. Theory"],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/jsait.2020.2983071","type":"journal-article","created":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T22:58:17Z","timestamp":1585090697000},"page":"324-335","source":"Crossref","is-referenced-by-count":58,"title":["PacGAN: The Power of Two Samples in Generative Adversarial Networks"],"prefix":"10.1109","volume":"1","author":[{"given":"Zinan","family":"Lin","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8856-1595","authenticated-orcid":false,"given":"Ashish","family":"Khetan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7671-2624","authenticated-orcid":false,"given":"Giulia","family":"Fanti","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8975-8306","authenticated-orcid":false,"given":"Sewoong","family":"Oh","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/2792745.2792775"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2014.80"},{"key":"ref71","author":"feizi","year":"2017","journal-title":"Understanding GANs The LQG setting"},{"key":"ref70","author":"liu","year":"2018","journal-title":"The inductive bias of restricted F-GANs"},{"key":"ref39","author":"mills","year":"2017","journal-title":"Phase space sampling and operator confidence with generative adversarial networks"},{"key":"ref74","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","author":"tolstikhin","year":"2017","journal-title":"Adagan Boosting generative models"},{"key":"ref75","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref33","first-page":"2008","article-title":"Secure multi-party differential privacy","author":"kairouz","year":"2015","journal-title":"Proc NeurIPS"},{"key":"ref32","first-page":"2879","article-title":"Extremal mechanisms for local differential privacy","author":"kairouz","year":"2014","journal-title":"Proc NeurIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2007.894680"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.872978"},{"key":"ref37","author":"goodfellow","year":"2016","journal-title":"Nips 2016 tutorial Generative adversarial networks"},{"key":"ref36","author":"lecun","year":"1998","journal-title":"The MNIST Database of Handwritten Digits"},{"key":"ref35","author":"radford","year":"2015","journal-title":"Unsupervised Representation learning with deep convolutional generative adversarial networks CoRR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2685505"},{"key":"ref60","article-title":"Spectral normalization for generative adversarial networks","author":"miyato","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref62","author":"finn","year":"2016","journal-title":"A connection between generative adversarial networks inverse reinforcement learning and energy-based models"},{"key":"ref61","author":"theis","year":"2015","journal-title":"A note on the evaluation of generative models"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/0609033"},{"key":"ref63","author":"wu","year":"2016","journal-title":"On the quantitative analysis of decoder-based generative models"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/18.104312"},{"key":"ref64","author":"santurkar","year":"2017","journal-title":"A classification-based perspective on GAN distributions"},{"key":"ref65","author":"richardson","year":"2018","journal-title":"On GANs and GMMs"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/18.669301"},{"key":"ref66","author":"arora","year":"2017","journal-title":"Theoretical limitations of encoder-decoder GAN architectures"},{"key":"ref67","author":"karras","year":"2017","journal-title":"Progressive growing of GANs for improved quality stability and variation"},{"key":"ref68","author":"liu","year":"2017","journal-title":"Approximation and convergence properties of generative adversarial learning"},{"key":"ref69","first-page":"1517","article-title":"Hilbert space embeddings and metrics on probability measures","volume":"11","author":"sriperumbudur","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729032"},{"key":"ref1","first-page":"1505","article-title":"PacGAN: The power of two samples in generative adversarial networks","author":"lin","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","first-page":"3308","article-title":"VEEGAN: Reducing mode collapse in GANs using implicit variational learning","author":"srivastava","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref22","author":"che","year":"2016","journal-title":"Mode regularized generative adversarial networks"},{"key":"ref21","author":"metz","year":"2016","journal-title":"Unrolled generative adversarial networks"},{"key":"ref24","first-page":"2667","article-title":"Dual discriminator generative adversarial nets","author":"nguyen","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref23","first-page":"3624","article-title":"Bayesian GANs","author":"saatci","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(59)90348-1"},{"key":"ref25","author":"arjovsky","year":"2017","journal-title":"Wasserstein GAN"},{"key":"ref50","author":"li","year":"2017","journal-title":"Towards Understanding the Dynamics of Generative Adversarial Networks"},{"key":"ref51","first-page":"5591","article-title":"Gradient descent GAN optimization is locally stable","author":"nagarajan","year":"2017","journal-title":"Proceedings of the 30th NeurIPS"},{"key":"ref59","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","author":"heusel","year":"2017","journal-title":"Proceedings of the 30th NeurIPS"},{"key":"ref58","first-page":"2015","article-title":"Stabilizing training of generative adversarial networks through regularization","author":"roth","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref57","first-page":"1823","article-title":"The numerics of GANs","author":"mescheder","year":"2017","journal-title":"Proceedings of the 30th NeurIPS"},{"key":"ref56","first-page":"5611","article-title":"Dualing GANs","author":"li","year":"2017","journal-title":"Proceedings of the 30th NeurIPS"},{"key":"ref55","author":"gulrajani","year":"2017","journal-title":"Improved training of wasserstein gans"},{"key":"ref54","author":"arora","year":"2017","journal-title":"Generalization and equilibrium in generative adversarial nets (gans)"},{"key":"ref53","first-page":"456","article-title":"F-GANs in an information geometric nutshell","author":"nock","year":"2017","journal-title":"Proceedings of the 30th NeurIPS"},{"key":"ref52","first-page":"271","article-title":"F-GAN: Training generative neural samplers using variational divergence minimization","author":"nowozin","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref10","author":"isola","year":"2016","journal-title":"Image-to-image translation with conditional adversarial networks"},{"key":"ref40","author":"arora","year":"2017","journal-title":"Do gans actually learn the distribution? an empirical study"},{"key":"ref11","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc NeurIPS"},{"key":"ref12","author":"kingma","year":"2018","journal-title":"Glow Generative flow with invertible 1×1 convolutions"},{"key":"ref13","author":"ilyas","year":"2017","journal-title":"The Robust Manifold Defense Adversarial Training using Generative Models"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref15","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref16","first-page":"2234","article-title":"Improved techniques for training GANs","author":"salimans","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref17","author":"reed","year":"2016","journal-title":"Generative adversarial text to image synthesis"},{"key":"ref18","author":"donahue","year":"2016","journal-title":"Adversarial feature learning"},{"key":"ref19","author":"dumoulin","year":"2016","journal-title":"Adversarially learned inference"},{"key":"ref4","author":"kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref3","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NeurIPS"},{"key":"ref6","first-page":"1486","article-title":"Deep generative image models using a Laplacian pyramid of adversarial networks","author":"denton","year":"2015","journal-title":"Proc NeurIPS"},{"key":"ref5","first-page":"926","article-title":"A practical guide to training restricted Boltzmann machines","volume":"9","author":"hinton","year":"2010","journal-title":"Momentum"},{"key":"ref8","first-page":"613","article-title":"Generating videos with scene dynamics","author":"vondrick","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref49","author":"bi?kowski","year":"2018","journal-title":"Demystifying mmd gans"},{"key":"ref7","first-page":"2852","article-title":"SeqGAN: Sequence generative adversarial nets with policy gradient","author":"yu","year":"2017","journal-title":"Proc AAAI"},{"key":"ref9","author":"ledig","year":"2016","journal-title":"Photo-realistic single image super-resolution using a generative adversarial network"},{"key":"ref46","first-page":"3391","article-title":"Deep sets","author":"zaheer","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref45","author":"kipf","year":"2016","journal-title":"Semi-supervised classification with graph convolutional networks"},{"key":"ref48","first-page":"2200","article-title":"MMD GAN: Towards deeper understanding of moment matching network","author":"li","year":"2017","journal-title":"Proceedings of the 30th NeurIPS"},{"key":"ref47","author":"sutherland","year":"2016","journal-title":"Generative models and model criticism via optimized maximum mean discrepancy"},{"key":"ref42","article-title":"AmbientGAN: Generative models from lossy measurements","author":"bora","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref41","author":"bora","year":"2017","journal-title":"Compressed sensing using generative models"},{"key":"ref44","author":"thekumparampil","year":"2018","journal-title":"Attention-based graph neural network for semi-supervised learning"},{"key":"ref43","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","author":"defferrard","year":"2016","journal-title":"Proc NeurIPS"}],"container-title":["IEEE Journal on Selected Areas in Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8700143\/8768428\/9046238-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8700143\/8768428\/09046238.pdf?arnumber=9046238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:17:31Z","timestamp":1651065451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9046238\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":75,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/jsait.2020.2983071","relation":{},"ISSN":["2641-8770"],"issn-type":[{"value":"2641-8770","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5]]}}}