{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,26]],"date-time":"2026-07-26T18:49:08Z","timestamp":1785091748815,"version":"3.55.0"},"reference-count":104,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Mag."],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1109\/msp.2020.3016905","type":"journal-article","created":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T21:10:26Z","timestamp":1614287426000},"page":"18-44","source":"Crossref","is-referenced-by-count":1198,"title":["Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing"],"prefix":"10.1109","volume":"38","author":[{"given":"Vishal","family":"Monga","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuelong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4358-5304","authenticated-orcid":false,"given":"Yonina C.","family":"Eldar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref6-sidebar6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.04-08-771"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2020.2964202"},{"key":"ref38","article-title":"Dense recurrent neural networks for inverse problems: History-cognizant unrolling of optimization algorithms","author":"hosseini","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2941271"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2737535"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2481418"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00919-9_5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2799231"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1629"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICDH.2018.00010"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/080716542"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2713099"},{"key":"ref29","article-title":"Deep unfolding: Model-based inspiration of novel deep architectures","author":"hershey","year":"2014"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1962.sp006837"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157583"},{"key":"ref21","first-page":"318","article-title":"Learning internal representations by error propagation","volume":"1","author":"rumelhart","year":"1986","journal-title":"Parallel Distributed Processing Explorations in the Microstructure of Cognition"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5555\/3327546.3327581"},{"key":"ref23","article-title":"ALISTA: Analytic weights are as good as learned weights in LISTA","author":"liu","year":"0","journal-title":"Proc Int Conf Learning Representation"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.50"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3934\/ipi.2009.3.487"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00853"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-012-0629-5"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294940"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00854"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2556683"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2042530"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2004.1381036"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2932116"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2926023"},{"key":"ref2-sidebar3","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13372"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.08.025"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2913500"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2895318"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.35"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00264"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"ref45","first-page":"111","author":"timofte","year":"0","journal-title":"Proc Asian Conf Computer Vision"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2477819"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2050625"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683124"},{"key":"ref41","article-title":"Dynamically unfolding recurrent restorer: A moving endpoint control method for image restoration","author":"zhang","year":"0","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref44","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc 32nd Int Conf Machine Learning"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1364\/OE.401925"},{"key":"ref73","first-page":"318","article-title":"Generic methods for optimization-based modeling","author":"domke","year":"0","journal-title":"Proc Artificial Intelligence and Statistics"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995320"},{"key":"ref1-sidebar1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511794308"},{"key":"ref71","first-page":"725","article-title":"Empirical risk minimization of graphical model parameters given approximate inference, decoding, and model structure","author":"stoyanov","year":"0","journal-title":"Proc Int Conf Artificial Intelligence and Statistics"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995520"},{"key":"ref76","first-page":"1608","article-title":"Learning generative models with Sinkhorn divergences","author":"genevay","year":"0","journal-title":"Proc 21st Int Conf Artificial Intelligence and Statistics"},{"key":"ref77","first-page":"733","article-title":"Sinkhorn AutoEncoders","author":"patrini","year":"0","journal-title":"Proc Conf Uncertainty Artificial Intelligence"},{"key":"ref74","first-page":"6694","article-title":"Neural expectation maximization","author":"greff","year":"0","journal-title":"Proc 31st Conf Neural Information Processing Systems"},{"key":"ref75","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume":"70","author":"arjovsky","year":"0","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref78","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"0","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref79","article-title":"Wasserstein auto-encoders","author":"tolstikhin","year":"0","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/72.279191"},{"key":"ref62","first-page":"133","article-title":"Training multilayer perceptrons with the extended Kalman algorithm","author":"singhal","year":"1989","journal-title":"Advances Neural Information Processing Systems"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1002\/0471221546"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.156"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2392779"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/34.56205"},{"key":"ref66","first-page":"6571","article-title":"Neural ordinary differential equations","author":"chen","year":"0","journal-title":"Proc 32nd Conf Neural Information Processing Systems"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045281"},{"key":"ref68","first-page":"3208","article-title":"PDE-Net: Learning PDEs from data","author":"long","year":"0","journal-title":"Proc 35th Int Conf Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2019.108925"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2972352"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2832656"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.198"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0909892106"},{"key":"ref5-sidebar6","doi-asserted-by":"publisher","DOI":"10.1038\/44565"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"ref90","article-title":"GAN dissection: Visualizing and understanding generative adversarial networks","author":"bau","year":"0","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref98","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proc Int Conf Aquatic Invasive Species"},{"key":"ref96","first-page":"5546","article-title":"Plug-and-play methods provably converge with properly trained denoisers","author":"ryu","year":"0","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref97","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"0","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref10","article-title":"Neural processes","author":"garnelo","year":"2018"},{"key":"ref11","article-title":"Functional variational Bayesian neural networks","author":"sun","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2760358"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104374"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2883941"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682542"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2596743"},{"key":"ref82","article-title":"Unrolled generative adversarial networks","author":"metz","year":"0","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref17","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"0","journal-title":"Proc Int Conf Artificial Intelligence and Statistics"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2904255"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_3"},{"key":"ref84","article-title":"Unrolled optimization with deep priors","author":"diamond","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"ref83","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref4-sidebar5","doi-asserted-by":"publisher","DOI":"10.5555\/2986459.2986472"},{"key":"ref80","first-page":"1","article-title":"Convolutional neural networks analyzed via convolutional sparse coding","volume":"18","author":"papyan","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858759"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2017.8227772"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/SiPS47522.2019.9020494"},{"key":"ref87","doi-asserted-by":"crossref","DOI":"10.4310\/CIS.2020.v20.n3.a2","article-title":"Data-driven symbol detection via model-based machine learning","author":"farsad","year":"2020"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3242022"},{"key":"ref3-sidebar5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"}],"container-title":["IEEE Signal Processing Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/79\/9363488\/09363511.pdf?arnumber=9363511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T00:58:03Z","timestamp":1671411483000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9363511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":104,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/msp.2020.3016905","relation":{},"ISSN":["1053-5888","1558-0792"],"issn-type":[{"value":"1053-5888","type":"print"},{"value":"1558-0792","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3]]}}}