{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:56:33Z","timestamp":1784134593610,"version":"3.55.0"},"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":"National Science Foundation","doi-asserted-by":"publisher","award":["1254204"],"award-info":[{"award-number":["1254204"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1738286"],"award-info":[{"award-number":["1738286"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-15-1-2677"],"award-info":[{"award-number":["N00014-15-1-2677"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1116589"],"award-info":[{"award-number":["1116589"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1302336"],"award-info":[{"award-number":["1302336"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1547332"],"award-info":[{"award-number":["1547332"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"industrial affiliates of NYU WIRELESS"},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1716388"],"award-info":[{"award-number":["1716388"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"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.2020.2986321","type":"journal-article","created":{"date-parts":[[2020,4,8]],"date-time":"2020-04-08T21:32:27Z","timestamp":1586381547000},"page":"336-347","source":"Crossref","is-referenced-by-count":26,"title":["Inference With Deep Generative Priors in High Dimensions"],"prefix":"10.1109","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2524-8817","authenticated-orcid":false,"given":"Parthe","family":"Pandit","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mojtaba","family":"Sahraee-Ardakan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0925-8169","authenticated-orcid":false,"given":"Sundeep","family":"Rangan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0939-7545","authenticated-orcid":false,"given":"Philip","family":"Schniter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3756-6580","authenticated-orcid":false,"given":"Alyson K.","family":"Fletcher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2014.6874830"},{"key":"ref72","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.2.021005"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2015.2496908"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1201\/b10905-6"},{"key":"ref39","first-page":"2177","article-title":"Expectation consistent approximate inference","volume":"6","author":"opper","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/57.1.97"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006578"},{"key":"ref33","first-page":"7440","article-title":"Plug-in estimation in high-dimensional linear inverse problems: A rigorous analysis","author":"fletcher","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952957"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2011.6033942"},{"key":"ref30","first-page":"1","article-title":"Message passing algorithms for compressed sensing","author":"donoho","year":"2010","journal-title":"Proc Inf Theory Workshop"},{"key":"ref37","first-page":"362","article-title":"Expectation propagation for approximate Bayesian inference","author":"minka","year":"2001","journal-title":"Proc Conf Uncertainty Artif Intell (UAI)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2916359"},{"key":"ref35","author":"barbier","year":"2017","journal-title":"Mutual Information and Optimality of Approximate Message-Passing in Random Linear Estimation"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2916100"},{"key":"ref60","author":"huang","year":"2018","journal-title":"A provably convergent scheme for compressive sensing under random generative priors"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2816681"},{"key":"ref61","author":"lei","year":"2019","journal-title":"Inverting deep generative models one layer at a time"},{"key":"ref63","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000001","article-title":"Graphical models, exponential families, and variational inference","volume":"1","author":"wainwright","year":"2008","journal-title":"Foundations & Trends in Mach Learn"},{"key":"ref28","first-page":"681","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","author":"welling","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref64","doi-asserted-by":"crossref","DOI":"10.1002\/9780470434697","author":"huber","year":"2009","journal-title":"Robust Statistics"},{"key":"ref27","author":"cheng","year":"2018","journal-title":"Sharp convergence rates for Langevin dynamics in the nonconvex setting"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2016.7869633"},{"key":"ref66","author":"fletcher","year":"2017","journal-title":"Inference in deep networks in high dimensions"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0909892106"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41589-5_6"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1137\/13090849X"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.850085"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849316"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2018.8437792"},{"key":"ref20","first-page":"2297","article-title":"Task-aware compressed sensing with generative adversarial networks","author":"kabkab","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref22","author":"tripathi","year":"2018","journal-title":"Correction by Projection Denoising Images with Generative Adversarial Networks"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462233"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"ref23","author":"mixon","year":"2018","journal-title":"Sunlayer Stable denoising with generative networks"},{"key":"ref26","author":"dumoulin","year":"2016","journal-title":"Adversarially learned inference"},{"key":"ref25","author":"yosinski","year":"2015","journal-title":"Understanding neural networks through deep visualization"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1802705116"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2016.7541382"},{"key":"ref59","author":"novak","year":"2018","journal-title":"Bayesian deep convolutional networks with many channels are Gaussian processes"},{"key":"ref58","author":"schoenholz","year":"2016","journal-title":"Deep information propagation"},{"key":"ref57","article-title":"On random deep weight-tied autoencoders: Exact asymptotic analysis, phase transitions, and implications to training","author":"li","year":"2019","journal-title":"Proc Int Conf Learn Res (ICLR)"},{"key":"ref56","first-page":"192","article-title":"The loss surfaces of multilayer networks","author":"choromanska","year":"2015","journal-title":"Proc Int Conf Artif Intell Stat"},{"key":"ref55","first-page":"571","article-title":"How to start training: The effect of initialization and architecture","author":"hanin","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2546221"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0745-0"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2016.7852290"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-010814-020120"},{"key":"ref11","first-page":"9446","article-title":"Deep image prior","author":"ulyanov","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2016.7541287"},{"key":"ref12","author":"veen","year":"2018","journal-title":"Compressed sensing with deep image prior and learned regularization"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344972"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-3242-6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2015.7447163"},{"key":"ref16","first-page":"1772","article-title":"Learned D-AMP: Principled neural network based compressive image recovery","author":"metzler","year":"2017","journal-title":"Proc Conf Neural Inf Process Syst (NIPS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2708040"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.627"},{"key":"ref19","author":"hand","year":"2017","journal-title":"Global guarantees for enforcing deep generative priors by empirical risk"},{"key":"ref4","first-page":"537","article-title":"Compressed sensing using generative models","author":"bora","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref3","author":"yeh","year":"2016","journal-title":"Semantic image inpainting with perceptual and contextual losses"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511794308"},{"key":"ref8","author":"kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref49","first-page":"1826","article-title":"Entropy and mutual information in models of deep neural networks","author":"gabri\u00e9","year":"2018","journal-title":"Proc Conf Neural Inf Process Syst (NIPS)"},{"key":"ref7","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","author":"rezende","year":"2014","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref9","author":"radford","year":"2015","journal-title":"Unsupervised Representation learning with deep convolutional generative adversarial networks CoRR"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2094817"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2619365"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2017.8262855"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iat004"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2653119"},{"key":"ref41","first-page":"192","article-title":"S-AMP: Approximate message passing for general matrix ensembles","author":"\u00e7akmak","year":"2014","journal-title":"Proc IEEE Inf Theory Workshop (ITW)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2014.6875083"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006899"}],"container-title":["IEEE Journal on Selected Areas in Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8700143\/8768428\/9061052-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8700143\/8768428\/09061052.pdf?arnumber=9061052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:17:32Z","timestamp":1651065452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9061052\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":75,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/jsait.2020.2986321","relation":{},"ISSN":["2641-8770"],"issn-type":[{"value":"2641-8770","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5]]}}}