{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T17:52:26Z","timestamp":1785952346759,"version":"3.56.0"},"reference-count":150,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001381","name":"Singapore National Research Foundation","doi-asserted-by":"publisher","award":["R-252-000-A74-281"],"award-info":[{"award-number":["R-252-000-A74-281"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Institute of Advanced Studies at the Technical University of Munich and the Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["456465471"],"award-info":[{"award-number":["456465471"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Institute of Advanced Studies at the Technical University of Munich and the Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["464123524"],"award-info":[{"award-number":["464123524"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Weizmann-UK Making Connections Programme","award":["129589"],"award-info":[{"award-number":["129589"]}]},{"DOI":"10.13039\/100012338","name":"Alan Turing Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012338","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Weizmann-UK Making Connections Programme","award":["129589"],"award-info":[{"award-number":["129589"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-1848087"],"award-info":[{"award-number":["DMS-1848087"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-2022205"],"award-info":[{"award-number":["DMS-2022205"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-2053448"],"award-info":[{"award-number":["DMS-2053448"]}],"id":[{"id":"10.13039\/100000001","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":[[2022,9]]},"DOI":"10.1109\/jsait.2023.3241123","type":"journal-article","created":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T19:52:51Z","timestamp":1675367571000},"page":"433-453","source":"Crossref","is-referenced-by-count":34,"title":["Theoretical Perspectives on Deep Learning Methods in Inverse Problems"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1403-9160","authenticated-orcid":false,"given":"Jonathan","family":"Scarlett","sequence":"first","affiliation":[{"name":"Department of Computer Science, the Department of Mathematics, Institute of Data Science, National University of Singapore, Queenstown, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2874-2984","authenticated-orcid":false,"given":"Reinhard","family":"Heckel","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8908-847X","authenticated-orcid":false,"given":"Miguel R. D.","family":"Rodrigues","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, University College London, London, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Hand","sequence":"additional","affiliation":[{"name":"College of Science and the Khoury College of Computer Sciences, Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4358-5304","authenticated-orcid":false,"given":"Yonina C.","family":"Eldar","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"When and how can deep generative models be inverted?","volume-title":"arXiv:2006.15555","author":"Aberdam","year":"2020"},{"key":"ref2","first-page":"1","article-title":"Learning step sizes for unfolded sparse coding","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Ablin"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"6371","DOI":"10.1109\/TSP.2021.3125601","article-title":"Deep learning model-aware regulatization with applications to inverse problems","volume":"69","author":"Amjad","year":"2021","journal-title":"IEEE Trans. Signal Process."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1907377117"},{"key":"ref5","first-page":"399","article-title":"Invertible generative models for inverse problems: Mitigating representation error and dataset bias","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Asim"},{"key":"ref6","first-page":"1","article-title":"Precise asymptotics for phase retrieval and compressed sensing with random generative priors","volume-title":"Proc. NeurIPS Workshop Deep Learn. Inverse Problems","author":"Aubin"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2020.3033985"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973075.95"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2548442"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87234-2_11"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2040894"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-007-9011-z"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1137\/080716542"},{"key":"ref14","article-title":"Compressive sensing and neural networks from a statistical learning perspective","volume-title":"arXiv:2010.15658","author":"Behboodi","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/jsait.2022.3220196"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1214\/08-AOS620"},{"key":"ref17","first-page":"537","article-title":"Compressed sensing using generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bora"},{"key":"ref18","first-page":"1","article-title":"AmbientGAN: Generative models from lossy measurements","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bora"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1364\/OPTICA.389314"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.858979"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2012.08.010"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.20124"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2016.2629286"},{"key":"ref24","first-page":"9079","article-title":"Theoretical linear convergence of unfolded ISTA and its practical weights and thresholds","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"31","author":"Chen"},{"key":"ref25","first-page":"11678","article-title":"Hyperparameter tuning is all you need for LISTA","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref26","first-page":"1240","article-title":"Understanding deep architectures with reasoning layer","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Chen"},{"key":"ref27","article-title":"Nonsmooth analysis and optimization","volume-title":"arXiv:1708.04180","author":"Clason","year":"2017"},{"key":"ref28","article-title":"Signal recovery with non-expansive generative network priors","volume-title":"arXiv:2204.13599","author":"Cocola","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1090\/S0894-0347-08-00610-3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2107151119"},{"key":"ref31","first-page":"4722","article-title":"Score-guided intermediate level optimization: Fast Langevin mixing for inverse problems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Daras"},{"key":"ref32","first-page":"2421","article-title":"Intermediate layer optimization for inverse problems using deep generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Daras"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1109\/TCI.2021.3097596","article-title":"Accelerated MRI with un-trained neural networks","volume":"7","author":"Darestani","year":"2021","journal-title":"IEEE Trans. Comput. Imag."},{"key":"ref34","first-page":"13917","article-title":"Constant-expansion suffices for compressed sensing with generative priors","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Daskalakis"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.20042"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511794308.002"},{"key":"ref37","first-page":"1222","article-title":"Modeling sparse deviations for compressed sensing using generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dhar"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"ref39","first-page":"1","article-title":"Gradient descent provably optimizes over-parameterized neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Du"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2030471"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511762321"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1561\/2200000092"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2018.8437792"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4948-7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39206-1_39"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933969"},{"key":"ref47","first-page":"12004","article-title":"Fast and provable ADMM for learning with generative priors","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"G\u00f3mez"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref49","article-title":"The troublesome kernel\u2014On hallucinations, no free lunches and the accuracy-stability trade-off in inverse problems","volume-title":"arXiv:2001.01258","author":"Gottschling","year":"2020"},{"key":"ref50","first-page":"399","article-title":"Learning fast approximations of sparse coding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gregor"},{"key":"ref51","article-title":"Regularized training of intermediate layers for generative models for inverse problems","volume-title":"arXiv:2203.04382","author":"Gunn","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1137\/070698920"},{"key":"ref53","first-page":"9154","article-title":"Phase retrieval under a generative prior","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Hand"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.4310\/CMS.2021.v19.n7.a11"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2019.2935447"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2935447"},{"key":"ref57","first-page":"1","article-title":"Deep decoder: Concise image representations from untrained non-convolutional networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Heckel"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaaa011"},{"key":"ref59","first-page":"1","article-title":"Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Heckel"},{"key":"ref60","first-page":"1","article-title":"Denoising and regularization via exploiting the structural bias of convolutional generators","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Heckel"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2210860"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s00041-021-09830-5"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5708"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1109\/TSP.2020.2977256","article-title":"Generative models for low-dimensional video representation and reconstruction","volume":"68","author":"Hyder","year":"2020","journal-title":"IEEE Trans. Signal Process."},{"key":"ref65","first-page":"8580","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Jacot"},{"key":"ref66","first-page":"14832","article-title":"Algorithmic guarantees for inverse imaging with untrained network priors","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Jagatap"},{"key":"ref67","first-page":"4709","article-title":"Instance-optimal compressed sensing via posterior sampling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jalal"},{"key":"ref68","first-page":"1","article-title":"Robust compressed sensing using generative models","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Jalal"},{"key":"ref69","article-title":"Just least squares: Binary compressive sampling with low generative intrinsic dimension","volume-title":"arXiv:2111.14486","author":"Jiao","year":"2021"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2713099"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1090\/conm\/026\/737400"},{"key":"ref72","first-page":"24719","article-title":"PLUGIn: A simple algorithm for inverting generative models with recovery guarantees","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Joshi"},{"key":"ref73","first-page":"5101","article-title":"On the power of compressed sensing with generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kamath"},{"key":"ref74","doi-asserted-by":"crossref","first-page":"5651","DOI":"10.1109\/TSP.2021.3117503","article-title":"LoRD-Net: Unfolded deep detection network with low-resolution receivers","volume":"69","author":"Khobahi","year":"2021","journal-title":"IEEE Trans. Signal Process."},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2991562"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref77","first-page":"2971","article-title":"Noise2Noise: Learning image restoration without clean data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lehtinen"},{"key":"ref78","first-page":"13910","article-title":"Inverting deep generative models, one layer at a time","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Lei"},{"key":"ref79","article-title":"Learned ISTA with error-based thresholding for adaptive sparse coding","volume-title":"arXiv:2112.10985","author":"Li","year":"2021"},{"key":"ref80","article-title":"Precise recovery of latent vectors from generative adversarial networks","volume-title":"arXiv:1702.04782","author":"Lipton","year":"2017"},{"key":"ref81","first-page":"1","article-title":"ALISTA: Analytic weights are as good as learned weights in LISTA","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref82","first-page":"5921","article-title":"Recovery analysis for plug-and-play priors using the restricted eigenvalue condition","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00033"},{"key":"ref84","first-page":"17656","article-title":"Towards sample-optimal compressive phase retrieval with sparse and generative priors","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref85","first-page":"6216","article-title":"Sample complexity bounds for 1-bit compressive sensing and binary stable embeddings with generative priors","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/454"},{"key":"ref87","first-page":"1","article-title":"Generative principal component analysis","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref88","first-page":"19125","article-title":"The generalized Lasso with nonlinear observations and generative priors","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Liu"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2980676"},{"key":"ref90","first-page":"9651","article-title":"Invertibility of convolutional generative networks from partial measurements","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"31","author":"Ma"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2739299"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.198"},{"key":"ref93","first-page":"1770","article-title":"Learned D-AMP: Principled neural network based compressive image recovery","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Metzler"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2556683"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3016905"},{"key":"ref97","first-page":"1","article-title":"Understanding trainable sparse coding with matrix factorization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Moreau"},{"key":"ref98","article-title":"Learning to sample: Data-driven sampling and reconstruction of FRI signals","volume-title":"arXiv:2106.14500","author":"Mulleti","year":"2021"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/jsait.2022.3219807"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2022.3179643"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2991563"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2983643"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/focs.2011.92"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746860"},{"key":"ref105","first-page":"7857","article-title":"Robust one-bit recovery via ReLU generative networks: Near-optimal statistical rate and global landscape analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qiu"},{"key":"ref106","first-page":"1674","article-title":"Non-convex learning via stochastic gradient Langevin dynamics: A nonasymptotic analysis","volume-title":"Proc. Conf. Learn. Theory","author":"Raginsky"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1137\/070697835"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2018.2880326"},{"key":"ref109","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.1109\/TSP.2022.3158588","article-title":"KalmanNet: Neural network aided Kalman filtering for partially known dynamics","volume":"70","author":"Revach","year":"2022","journal-title":"IEEE Trans. Signal Process."},{"key":"ref110","article-title":"Untrained graph neural networks for denoising","volume-title":"arXiv:2109.11700","author":"Rey","year":"2021"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1137\/16M1102884"},{"key":"ref112","first-page":"4763","article-title":"The convergence rate of neural networks for learned functions of different frequencies","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Ronen"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref114","article-title":"Inferring a continuous distribution of atom coordinates from cryo-EM images using VAEs","volume-title":"arXiv:2106.14108","author":"Rosenbaum","year":"2021"},{"key":"ref115","first-page":"5546","article-title":"Plug-and-play methods provably converge with properly trained denoisers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ryu"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3129995"},{"key":"ref117","article-title":"Generalization error bounds for iterative recovery algorithms unfolded as neural networks","volume-title":"arXiv:2112.04364","author":"Schnoor","year":"2021"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2481418"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462233"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1561\/2000000113"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3218802"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2972352"},{"key":"ref123","article-title":"Model-based machine learning for communications","volume-title":"arXiv:2101.04726","author":"Shlezinger","year":"2021"},{"key":"ref124","first-page":"1","article-title":"Generalization and estimation error bounds for model-based neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Shultzman"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.24.1.1193"},{"key":"ref126","first-page":"7462","article-title":"Implicit neural representations with periodic activation functions","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Sitzmann"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2941271"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2854560"},{"key":"ref129","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1109\/TCI.2021.3094062","article-title":"Scalable plug-and-play ADMM with convergence guarantees","volume":"7","author":"Sun","year":"2021","journal-title":"IEEE Trans. Comput. Imag."},{"key":"ref130","first-page":"1","article-title":"Intriguing properties of neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Szegedy"},{"key":"ref131","first-page":"1","article-title":"Unsupervised learning from incomplete measurements for inverse problems","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Tachella"},{"key":"ref132","first-page":"1","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Tancik"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2875569"},{"key":"ref134","first-page":"9446","article-title":"Deep image prior","volume-title":"Proc. Conf. Comput. Vis. Pattern Recognit.","author":"Ulyanov"},{"key":"ref135","article-title":"Compressed sensing with deep image prior and learned regularization","volume-title":"arXiv:1806.06438","author":"Van Veen","year":"2018"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2013.6737048"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511794308.006"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1038\/s41377-020-0302-3"},{"key":"ref139","first-page":"6697","article-title":"On the statistical rate of nonlinear recovery in generative models with heavy-tailed data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wei"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01037"},{"key":"ref141","first-page":"1","article-title":"Sparse coding with gated learned ISTA","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wu"},{"key":"ref142","first-page":"6828","article-title":"Learning a compressed sensing measurement matrix via gradient unrolling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1137\/120869997"},{"key":"ref144","first-page":"4340","article-title":"Maximal sparsity with deep networks?","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Xin"},{"key":"ref145","article-title":"Semantic image inpainting with perceptual and contextual losses","volume-title":"arXiv:1607.07539","author":"Yeh","year":"2016"},{"key":"ref146","article-title":"Outlier detection using generative models with theoretical performance guarantees","volume-title":"arXiv:1810.11335","author":"Yi","year":"2018"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3084288"},{"key":"ref148","volume-title":"Dive into deep learning","author":"Zhang","year":"2022"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2926023"},{"key":"ref150","first-page":"1","article-title":"Reconstructing continuous distributions of 3D protein structure from cryo-EM images","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhong"}],"container-title":["IEEE Journal on Selected Areas in Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8700143\/10077203\/10035380-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8700143\/10077203\/10035380.pdf?arnumber=10035380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T13:06:59Z","timestamp":1707829619000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10035380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9]]},"references-count":150,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/jsait.2023.3241123","relation":{},"ISSN":["2641-8770"],"issn-type":[{"value":"2641-8770","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9]]}}}