{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T16:25:08Z","timestamp":1790439908387,"version":"4.1.0"},"reference-count":203,"publisher":"Emerald","issue":"2-3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,5]]},"abstract":"<jats:p>This review discusses methods for learning parameters for image reconstruction problems using bilevel formulations.Image reconstruction typically involves optimizing a cost function to recover a vector of unknown variables that agrees with collected measurements and prior assumptions. Stateof-the-art image reconstruction methods learn these prior assumptions from training data using various machine learning techniques, such as bilevel methods.<\/jats:p>\n                  <jats:p>One can view the bilevel problem as formalizing hyperparameter optimization, as bridging machine learning and cost function based optimization methods, or as a method to learn variables best suited to a specific task. More formally, bilevel problems attempt to minimize an upper-level loss function, where variables in the upper-level loss function are themselves minimizers of a lower-level cost function.<\/jats:p>\n                  <jats:p>This review contains a running example problem of learning tuning parameters and the coefficients for sparsifying filters used in a regularizer. Such filters generalize the popular total variation regularization method, and learned filters are closely related to convolutional neural networks approaches that are rapidly gaining in popularity. Here, the lower-level problem is to reconstruct an image using a regularizer with learned sparsifying filters; the corresponding upper-level optimization problem involves a measure of reconstructed image quality based on training data.<\/jats:p>\n                  <jats:p>This review discusses multiple perspectives to motivate the use of bilevel methods and to make them more easily accessible to different audiences. We then turn to ways to optimize the bilevel problem, providing pros and cons of the variety of proposed approaches. Finally we overview bilevel applications in image reconstruction.<\/jats:p>","DOI":"10.1561\/2000000111","type":"journal-article","created":{"date-parts":[[2022,5,5]],"date-time":"2022-05-05T07:00:36Z","timestamp":1651734036000},"page":"121-289","source":"Crossref","is-referenced-by-count":33,"title":["Bilevel Methods for Image Reconstruction"],"prefix":"10.1108","volume":"15","author":[{"given":"Caroline","family":"Crockett","sequence":"first","affiliation":[{"name":"Department of EECS, University of Michigan , Ann Arbor, Michigan,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey A.","family":"Fessler","sequence":"additional","affiliation":[{"name":"Department of EECS, University of Michigan , Ann Arbor, Michigan,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"140","published-online":{"date-parts":[[2022,5,5]]},"reference":[{"issue":"10","key":"2026040902314272700_ref001","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1088\/1361-6420\/ac245d","article-title":"Learning regularization parameters of inverse problems via deep neural networks,","volume":"37","author":"Afkham","year":"2021","journal-title":"Inverse Problems"},{"key":"2026040902314272700_ref002","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/ab80d7","article-title":"Bilevel optimization, deep learning and fractional laplacian regularization with applications in tomography,","author":"Antil","journal-title":"Inverse Problems"},{"key":"2026040902314272700_ref003","article-title":"Deep equilibrium models,","volume":"32","author":"Bai","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"7","key":"2026040902314272700_ref004","doi-asserted-by":"publisher","first-page":"1266","DOI":"10.1364\/JOSAA.7.001266","article-title":"Objective assessment of image quality: Effects of quantum noise and object variability,","volume":"7","author":"Barrett","year":"1990","journal-title":"J. Opt. Soc. Am. A"},{"issue":"2-3","key":"2026040902314272700_ref005","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/s10915-012-9650-3","article-title":"Higher-order TV methods\u2014Enhancement via Bregman iteration,","volume":"54","author":"Benning","year":"2013","journal-title":"Journal of Scientific Computing"},{"key":"2026040902314272700_ref006","doi-asserted-by":"publisher","first-page":"281","DOI":"10.5555\/2188385.2188395","article-title":"Random search for hyper-parameter optimization,","volume":"13","author":"Bergstra","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"2026040902314272700_ref007","volume-title":"The Theory of Evolution Strategies, ser. Natural Computing Series","author":"Beyer","year":"2001"},{"issue":"1","key":"2026040902314272700_ref008","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1137\/141000671","article-title":"Julia: A fresh approach to numerical computing,","volume":"59","author":"Bezanson","year":"2017","journal-title":"SIAM Review"},{"key":"2026040902314272700_ref009","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-030-61598-7_2","article-title":"Deep parallel MRI reconstruction network without coil sensitivities,","author":"Bian","year":"2020","journal-title":"Machine Learning for Medical Image Reconstruction"},{"key":"2026040902314272700_ref010","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/978-0-387-31256-9_3","article-title":"Fenchel Duality,","author":"Borwein","year":"2006","journal-title":"Convex Analysis and Nonlinear Optimization: Theory and Examples"},{"issue":"1","key":"2026040902314272700_ref011","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1109\/TIP.2017.2760518","article-title":"Deep neural networks for no-reference and full-reference image quality assessment,","volume":"27","author":"Bosse","year":"2018","journal-title":"IEEE Transactions on Image Processing"},{"key":"2026040902314272700_ref012","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1137\/090769521","article-title":"Total generalized variation,","volume":"3","author":"Bredies","year":"2010","journal-title":"SIAM Journal on Imaging Sciences"},{"issue":"5","key":"2026040902314272700_ref013","doi-asserted-by":"publisher","first-page":"1190","DOI":"10.1137\/0916069","article-title":"A limited memory algorithm for bound constrained optimization,","volume":"16","author":"Byrd","year":"1995","journal-title":"SIAM J. Sci. Comp."},{"key":"2026040902314272700_ref014","article-title":"Bilevel approaches for learning of variational imaging models,","volume":"18","author":"Calatroni","year":"2017","journal-title":"Variational Methods in Imaging and Geometric Control"},{"issue":"2","key":"2026040902314272700_ref015","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1109\/TIT.2005.862083","article-title":"Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information,","volume":"52","author":"Candes","year":"2006","journal-title":"IEEE Transactions on Information Theory"},{"issue":"1","key":"2026040902314272700_ref016","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.acha.2010.10.002","article-title":"Compressed sensing with coherent and redundant dictionaries,","volume":"31","author":"Cand\u00e8s","year":"2011","journal-title":"Applied and Computational Harmonic Analysis"},{"key":"2026040902314272700_ref017","doi-asserted-by":"crossref","article-title":"Scalable subspace methods for derivative-free nonlinear least-squares optimization.","author":"Cartis","DOI":"10.1007\/s10107-022-01836-1"},{"issue":"2","key":"2026040902314272700_ref018","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/s002110050258","article-title":"Image recovery via total variation minimization and related problems,","volume":"76","author":"Chambolle","journal-title":"Numerische Mathematik"},{"key":"2026040902314272700_ref019","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1017\/S096249291600009X","article-title":"An introduction to continuous optimization for imaging,","volume":"25","author":"Chambolle","journal-title":"Acta Numerica"},{"issue":"1-2","key":"2026040902314272700_ref020","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/s10107-015-0957-3","article-title":"On the ergodic convergence rates of a first-order primal\u2014dual algorithm,","volume":"159","author":"Chambolle","year":"2016","journal-title":"Mathematical Programming: Series A and B"},{"issue":"2","key":"2026040902314272700_ref021","doi-asserted-by":"publisher","first-page":"778","DOI":"10.1137\/20M1377199","article-title":"Learning consistent discretizations of the total variation,","volume":"14","author":"Chambolle","year":"2021"},{"key":"2026040902314272700_ref022","article-title":"Neural Ordinary Differential Equations,","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026040902314272700_ref023","article-title":"A single-timescale stochastic bilevel optimization method.","author":"Chen"},{"key":"2026040902314272700_ref024","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1007\/978-3-642-40602-7_30","article-title":"Revisiting loss-specific training of filter-based MRFs for image restoration,","author":"Weickert","year":"2013","journal-title":"Pattern Recognition"},{"issue":"3","key":"2026040902314272700_ref025","doi-asserted-by":"publisher","first-page":"1060","DOI":"10.1109\/TIP.2014.2299065","article-title":"Insights into analysis operator learning: From patch-based sparse models to higher order MRFs,","volume":"23","author":"Chen","year":"2014","journal-title":"IEEE Transactions on Image Processing"},{"issue":"4","key":"2026040902314272700_ref026","doi-asserted-by":"publisher","first-page":"1532","DOI":"10.1137\/20M1353368","article-title":"Learnable descent algorithm for nonsmooth nonconvex image reconstruction,","volume":"14","author":"Chen","year":"2021","journal-title":"SIAM Journal on Imaging Sciences"},{"issue":"1","key":"2026040902314272700_ref027","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1137\/18M1225707","article-title":"Gradient-based solution algorithms for a class of bilevel optimization and optimal control problems with a nonsmooth lower level,","volume":"30","author":"Christof","journal-title":"SIAM Journal on Optimization"},{"issue":"4","key":"2026040902314272700_ref028","doi-asserted-by":"publisher","first-page":"1697","DOI":"10.1109\/TIP.2017.2761545","article-title":"Convolutional dictionary learning: Acceleration and convergence,","volume":"27","author":"Chun","journal-title":"IEEE Trans. Im. Proc."},{"key":"2026040902314272700_ref029","doi-asserted-by":"publisher","first-page":"2020","DOI":"10.1109\/TIP.2019.2937734","article-title":"Convolutional analysis operator learning: Acceleration and convergence,","volume":"29","author":"Chun","journal-title":"IEEE Transactions on Image Processing"},{"issue":"1","key":"2026040902314272700_ref030","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/s10479-007-0176-2","article-title":"An overview of bilevel optimization,","volume":"153","author":"Colson","journal-title":"Annals of Operations Research"},{"key":"2026040902314272700_ref031","doi-asserted-by":"publisher","volume-title":"Trust Region Methods","author":"Conn","DOI":"10.1137\/1.9780898719857"},{"key":"2026040902314272700_ref032","author":"Crockett","year":"2022","journal-title":"BilevelFilterLearningForImageRecon"},{"key":"2026040902314272700_ref033","doi-asserted-by":"publisher","first-page":"2803","DOI":"10.1109\/ICIP42928.2021.9506489","article-title":"Motivating bilevel approaches to filter learning: A case study,","author":"Crockett","journal-title":"2021 IEEE International Conference on Image Processing (ICIP)"},{"key":"2026040902314272700_ref034","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1109\/CAMSAP45676.2019.9022669","article-title":"Incorporating handcrafted filters in convolutional analysis operator learning for ill-posed inverse problems,","author":"Crockett","journal-title":"2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)"},{"key":"2026040902314272700_ref035","doi-asserted-by":"crossref","volume-title":"Bilevel parameter optimization for learning nonlocal image denoising models","author":"D\u2019Elia","DOI":"10.2172\/1617438"},{"issue":"8","key":"2026040902314272700_ref036","doi-asserted-by":"publisher","first-page":"2080","DOI":"10.1109\/TIP.2007.901238","article-title":"Image denoising by sparse 3-D transform-domain collaborative filtering,","volume":"16","author":"Dabov","journal-title":"IEEE Transactions on Image Processing"},{"key":"2026040902314272700_ref037","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1007\/11758549_78","article-title":"The data-flow equations of check-pointing in reverse automatic differentiation,","author":"Dauvergne","year":"2006","journal-title":"International Conference on Computational Science"},{"issue":"1","key":"2026040902314272700_ref038","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10851-016-0662-8","article-title":"Bilevel parameter learning for higher-order total variation regularisation models,","volume":"57","author":"Reyes","journal-title":"Journal of Mathematical Imaging and Vision"},{"issue":"4","key":"2026040902314272700_ref039","doi-asserted-by":"publisher","first-page":"2448","DOI":"10.1137\/140968045","article-title":"Stein Unbiased GrAdient estimator of the Risk (SUGAR) for multiple parameter selection,","volume":"7","author":"Deledalle","journal-title":"SIAM Journal on Imaging Sciences"},{"issue":"1-2","key":"2026040902314272700_ref040","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/s10107-010-0342-1","article-title":"Is bilevel programming a special case of a mathematical program with complementarity constraints?","volume":"131","author":"Dempe","journal-title":"Mathematical Programming"},{"issue":"3","key":"2026040902314272700_ref041","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1080\/0233193031000149894","article-title":"Annotated bibliography on bilevel programming and mathematical programs with equilibrium constraints,","volume":"52","author":"Dempe","journal-title":"Optimization"},{"key":"2026040902314272700_ref042","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-52119-6","volume-title":"Bilevel Optimization: Advances and next Challenges","author":"Dempe","year":"2020"},{"key":"2026040902314272700_ref043","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jco.2016.11.001","article-title":"The exact information-based complexity of smooth convex minimization,","volume":"39","author":"Drori","journal-title":"J. Complexity"},{"issue":"1-3","key":"2026040902314272700_ref044","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/BF01581204","article-title":"On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators,","volume":"55","author":"Eckstein","journal-title":"Mathematical Programming"},{"issue":"3","key":"2026040902314272700_ref045","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1007\/s10851-019-00926-8","article-title":"Variational networks: An optimal control approach to early stopping variational methods for image restoration,","volume":"62","author":"Effland","journal-title":"Journal of Mathematical Imaging and Vision"},{"issue":"6","key":"2026040902314272700_ref046","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1007\/s10851-021-01020-8","article-title":"Inexact derivative-free optimization for bilevel learning,","volume":"63","author":"Ehrhardt","year":"2021","journal-title":"Journal of Mathematical Imaging and Vision"},{"key":"2026040902314272700_ref047","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-7011-4","volume-title":"Sparse and redundant representations: from theory to applications in signal and image processing","author":"Elad","year":"2010"},{"issue":"3","key":"2026040902314272700_ref048","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1088\/0266-5611\/23\/3\/007","article-title":"Analysis versus synthesis in signal priors,","volume":"23","author":"Elad","journal-title":"Inverse Problems"},{"key":"2026040902314272700_ref049","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511794308","volume-title":"Compressed sensing: Theory and applications","author":"Eldar","year":"2012"},{"issue":"4","key":"2026040902314272700_ref050","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1561\/2000000008","article-title":"Rethinking biased estimation: Improving maximum likelihood and the Cramer-Rao bound,","volume":"1","author":"Eldar","year":"2008","journal-title":"Found. & Trends in Sig. Pro."},{"issue":"2","key":"2026040902314272700_ref051","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1109\/TSP.2008.2008212","article-title":"Generalized SURE for exponential families: Applications to regularization,","volume":"57","author":"Eldar","journal-title":"IEEE Transactions on Signal Processing"},{"key":"2026040902314272700_ref052","doi-asserted-by":"crossref","DOI":"10.1007\/978-94-009-1740-8","volume-title":"Regularization of inverse problems","author":"Engl","year":"1996"},{"key":"2026040902314272700_ref053","volume-title":"510k premarket notification of Deep Learning Image Reconstruction (GE Medical Systems)","author":"FDA","year":"2019"},{"key":"2026040902314272700_ref054","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/978-3-319-18461-6_10","article-title":"Bilevel image denoising using gaussianity tests,","volume":"9087","author":"Fehrenbach","year":"2015","journal-title":"International Conference on Scale Space and Variational Methods in Computer Vision"},{"issue":"3","key":"2026040902314272700_ref055","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1109\/83.491322","article-title":"Mean and variance of implicitly defined biased estimators (such as penalized maximum likelihood): Applications to tomography,","volume":"5","author":"Fessler","journal-title":"IEEE Trans. Im. Proc."},{"issue":"4","key":"2026040902314272700_ref056","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1109\/MSP.2010.936726","article-title":"Model-based image reconstruction for MRI,","volume":"27","author":"Fessler","journal-title":"IEEE Sig. Proc. Mag."},{"issue":"1","key":"2026040902314272700_ref057","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/MSP.2019.2943645","article-title":"Optimization methods for MR image reconstruction,","volume":"37","author":"Fessler","journal-title":"IEEE Sig. Proc. Mag."},{"issue":"9","key":"2026040902314272700_ref058","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1109\/83.535846","article-title":"Spatial resolution properties of penalized-likelihood image reconstruction methods: Spaceinvariant tomographs,","volume":"5","author":"Fessler","journal-title":"IEEE Trans. Im. Proc."},{"key":"2026040902314272700_ref059","volume-title":"MIRT-demo: 01-recon","author":"Fessler"},{"key":"2026040902314272700_ref060","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-05318-5","article-title":"Chapter 1: Hyperparameter optimization,","author":"Feurer","year":"2019","journal-title":"Automated Machine Learning: Methods, Systems, Challenges"},{"key":"2026040902314272700_ref061","article-title":"Numerical experience with solving MPECs as NLPs,","author":"Fletcher","year":"2002","journal-title":"Department of Mathematics and Computer Science, University of Dundee"},{"key":"2026040902314272700_ref062","article-title":"Efficient multiple hyperparameter learning for log-linear models,","volume":"20","author":"Foo","year":"2007","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026040902314272700_ref063","first-page":"1165","article-title":"Forward and reverse gradient-based hyperparameter optimization,","author":"Franceschi","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"2026040902314272700_ref064","first-page":"1568","article-title":"Bilevel programming for hyperparameter optimization and metalearning,","author":"Franceschi","journal-title":"International Conference on Machine Learning"},{"key":"2026040902314272700_ref065","article-title":"A tutorial on bayesian optimization.","author":"Frazier"},{"key":"2026040902314272700_ref066","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v36i6.20619","article-title":"JFB: Jacobian-free backpropagation for implicit networks,","author":"Fung","year":"2022","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"3","key":"2026040902314272700_ref067","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1109\/TCI.2018.2840334","article-title":"Convolutional dictionary dearning: A comparative review and new algorithms,","volume":"4","author":"Garcia-Cardona","journal-title":"IEEE Transactions on Computational Imaging"},{"key":"2026040902314272700_ref068","article-title":"HARK side of deep learning \u2013 From grad student descent to automated machine learning.","author":"Gencoglu"},{"key":"2026040902314272700_ref069","article-title":"Approximation methods for bilevel programming.","author":"Ghadimi"},{"issue":"2","key":"2026040902314272700_ref070","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1007\/s10278-019-00274-4","article-title":"Deep learning for low-dose CT denoising using perceptual loss and edge detection layer,","volume":"33","author":"Gholizadeh-Ansari","year":"2020","journal-title":"J. Digital Im."},{"key":"2026040902314272700_ref071","volume-title":"Questions about BLORC","author":"Ghosh"},{"key":"2026040902314272700_ref072","volume-title":"Bilevel learning of l1-regularizers with closed-form gradients(BLORC)","author":"Ghosh"},{"key":"2026040902314272700_ref073","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1109\/TCI.2021.3118944","article-title":"Deep equilibrium architectures for inverse problems in imaging,","volume":"7","author":"Gilton","year":"2021","journal-title":"IEEE Transactions on Computational Imaging"},{"issue":"3","key":"2026040902314272700_ref074","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1016\/j.acha.2010.11.005","article-title":"The projected GSURE for automatic parameter tuning in iterative shrinkage methods,","volume":"30","author":"Giryes","journal-title":"Applied and Computational Harmonic Analysis"},{"issue":"2","key":"2026040902314272700_ref075","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1080\/00401706.1979.10489751","article-title":"Generalized crossvalidation as a method for choosing a good ridge parameter,","volume":"21","author":"Golub","journal-title":"Technometrics"},{"issue":"6","key":"2026040902314272700_ref076","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1137\/0717073","article-title":"An analysis of the total least squares problem,","volume":"17","author":"Golub","journal-title":"SIAM J. Numer. Anal."},{"key":"2026040902314272700_ref077","article-title":"On differentiating parameterized argmin and argmax problems with application to bi-level optimization.","author":"Gould"},{"issue":"6","key":"2026040902314272700_ref078","doi-asserted-by":"publisher","first-page":"1394","DOI":"10.1109\/TMI.2018.2832540","article-title":"Learning-based compressive MRI,","volume":"37","author":"Gozcu","journal-title":"IEEE Trans. Med. Imag."},{"key":"2026040902314272700_ref079","article-title":"On the iteration complexity of hypergradient computation,","volume":"11","author":"Grazzi","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning"},{"key":"2026040902314272700_ref080","article-title":"Learning fast approximations of sparse coding,","author":"Gregor","year":"2010","journal-title":"Proc. Intl. Conf. Mach. Learn"},{"issue":"1","key":"2026040902314272700_ref081","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1109\/MSP.2013.2273004","article-title":"Image inpainting: Overview and recent advances,","volume":"31","author":"Guillemot","journal-title":"IEEE Sig. Proc. Mag."},{"issue":"3","key":"2026040902314272700_ref082","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1088\/0266-5611\/19\/3\/309","article-title":"Learning regularization functionals a supervised training approach,","volume":"19","author":"Haber","journal-title":"Inverse Problems"},{"issue":"6","key":"2026040902314272700_ref083","doi-asserted-by":"publisher","first-page":"3055","DOI":"10.1002\/mrm.26977","article-title":"Learning a variational network for reconstruction of accelerated MRI data,","volume":"79","author":"Hammernik","year":"2018","journal-title":"Magnetic Resonance in Medicine"},{"key":"2026040902314272700_ref084","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/B978-0-12-816176-0.00007-7","article-title":"Machine learning for image reconstruction,","author":"Hammernik","year":"2020","journal-title":"Handbook of Medical Image Computing and Computer Assisted Intervention"},{"issue":"6","key":"2026040902314272700_ref085","doi-asserted-by":"publisher","first-page":"2138","DOI":"10.1109\/TIP.2013.2246175","article-title":"Analysis operator learning and its application to image reconstruction,","volume":"22","author":"Hawe","journal-title":"IEEE Transactions on Image Processing"},{"issue":"2","key":"2026040902314272700_ref086","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1109\/79.487040","article-title":"Neural networks expand SP\u2019s horizons,","volume":"13","author":"Haykin","journal-title":"IEEE Sig. Proc. Mag."},{"issue":"2","key":"2026040902314272700_ref087","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1109\/TMI.2018.2865202","article-title":"Optimizing a parameterized plug-and-play ADMM for iterative low-dose CT reconstruction,","volume":"38","author":"He","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"1","key":"2026040902314272700_ref088","doi-asserted-by":"publisher","DOI":"10.1186\/s13663-021-00706-3","article-title":"Feasibility-based fixed point networks,","volume":"2021","author":"Heaton","journal-title":"Fixed Point Theory and Algorithms for Sciences and Engineering"},{"issue":"9","key":"2026040902314272700_ref089","doi-asserted-by":"publisher","first-page":"2290","DOI":"10.1109\/78.157228","article-title":"Statistic-based MAP image reconstruction from Poisson data using Gibbs priors,","volume":"40","author":"Hebert","journal-title":"IEEE Trans. Sig. Proc."},{"key":"2026040902314272700_ref090","doi-asserted-by":"crossref","article-title":"Dualization and automatic distributed parameter selection of total generalized variation via bilevel optimization.","author":"Hinterm\u00fcller","DOI":"10.1080\/01630563.2022.2069812"},{"issue":"4","key":"2026040902314272700_ref091","doi-asserted-by":"publisher","first-page":"1139","DOI":"10.3934\/ipi.2015.9.1139","article-title":"Bilevel optimization for calibrating point spread functions in blind deconvolution,","volume":"9","author":"Hinterm\u00fcller","year":"2015","journal-title":"Inverse Problems & Imaging"},{"key":"2026040902314272700_ref092","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/978-3-642-40395-8_12","article-title":"An optimal control approach to find sparse data for Laplace interpolation,","volume":"8081","author":"Hoeltgen","year":"2013","journal-title":"Energy Minimization Methods in Computer Vision and Pattern Recognition"},{"issue":"9","key":"2026040902314272700_ref093","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1080\/03610927708827533","article-title":"Robust regression using iteratively reweighted least-squares,","volume":"6","author":"Holland","year":"1977","journal-title":"Comm. in Statistics\u2014Theory and Methods"},{"issue":"11","key":"2026040902314272700_ref094","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1088\/1361-6420\/aade77","article-title":"A bilevel approach for parameter learning in inverse problems,","volume":"34","author":"Holler","journal-title":"Inverse Problems"},{"key":"2026040902314272700_ref095","volume-title":"A two-timescale framework for bilevel optimization: Complexity analysis and application to actor-critic","author":"Hong"},{"issue":"6","key":"2026040902314272700_ref096","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1109\/79.637299","article-title":"The past, present, and future of neural networks for signal processing,","volume":"14","author":"Hwang","journal-title":"IEEE Sig. Proc. Mag."},{"issue":"3-4","key":"2026040902314272700_ref097","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1561\/2200000058","article-title":"Non-convex optimization for machine learn-ing,","volume":"10","author":"Jain","year":"2017","journal-title":"Found. & Trends in Machine Learning"},{"key":"2026040902314272700_ref098","first-page":"4882","article-title":"Bilevel optimization: Convergence analysis and enhanced design,","author":"Ji","journal-title":"Proceedings of the 38th International Conference on Machine Learning"},{"issue":"9","key":"2026040902314272700_ref099","doi-asserted-by":"publisher","first-page":"4509","DOI":"10.1109\/TIP.2017.2713099","article-title":"Deep convolutional neural network for inverse problems in imaging,","volume":"26","author":"Jin","journal-title":"IEEE Trans. Im. Proc."},{"issue":"2","key":"2026040902314272700_ref100","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1016\/j.cam.2005.09.027","article-title":"Statistical inverse problems: Discretization, model reduction and inverse crimes,","volume":"198","author":"Kaipioa","journal-title":"J. Comp. Appl. Math."},{"key":"2026040902314272700_ref101","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.1109\/CVPR.2014.224","article-title":"Convolutional neural networks for no-reference image quality assessment,","author":"Kang","journal-title":"2014 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"2026040902314272700_ref102","doi-asserted-by":"publisher","first-page":"1403","DOI":"10.1109\/TCI.2020.3025735","article-title":"Memory-efficient learning for large-scale computational imaging,","volume":"6","author":"Kellman","year":"2020","journal-title":"IEEE Transactions on Computational Imaging"},{"key":"2026040902314272700_ref103","first-page":"13","article-title":"A near-optimal algorithm for stochastic bilevel optimization via double-momentum,","author":"Khanduri","year":"2021","journal-title":"35th Conference on Neural Information Processing Systems (NeurIPS 2021)"},{"issue":"1","key":"2026040902314272700_ref104","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1007\/s10957-018-1287-4","article-title":"Adaptive restart of the optimized gradient method for convex optimization,","volume":"178","author":"Kim","journal-title":"J. Optim. Theory Appl."},{"issue":"1","key":"2026040902314272700_ref105","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s10957-016-1018-7","article-title":"On the convergence analysis of the optimized gradient method,","volume":"172","author":"Kim","journal-title":"Journal of Optimization Theory and Applications"},{"issue":"6","key":"2026040902314272700_ref106","doi-asserted-by":"publisher","first-page":"1112","DOI":"10.1109\/JSTSP.2020.3007326","article-title":"Unsupervised training of denoisers for low-dose CT reconstruction without full-dose ground truth,","volume":"14","author":"Kim","journal-title":"IEEE J. Sel. Top. Sig. Proc."},{"key":"2026040902314272700_ref107","article-title":"Adam: A method for stochastic optimization,","volume":"1412.6980","author":"Kingma","journal-title":"3rd International Conference on Learning Representations"},{"issue":"2","key":"2026040902314272700_ref108","doi-asserted-by":"publisher","first-page":"4945","DOI":"10.1214\/17-EJS1335SI","article-title":"Fast Bayesian hyperparameter optimization on large datasets,","volume":"11","author":"Klein","year":"2017","journal-title":"Electron. J. Statist."},{"key":"2026040902314272700_ref109","doi-asserted-by":"publisher","first-page":"7897","DOI":"10.1109\/CVPR42600.2020.00792","article-title":"Belief propagation reloaded: Learning BP-layers for labeling problems,","author":"Kn\u00f6belreiter","journal-title":"presented at the The IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"issue":"2","key":"2026040902314272700_ref110","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1002\/mrm.22595","article-title":"Second order total generalized variation (TGV) for MRI,","volume":"65","author":"Knoll","year":"2011","journal-title":"Mag. Res. Med."},{"key":"2026040902314272700_ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3124086","article-title":"Total deep variation: A stable regularization method for inverse problems,","author":"Kobler","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"issue":"10","key":"2026040902314272700_ref112","doi-asserted-by":"publisher","first-page":"4439","DOI":"10.1002\/mp.13151","article-title":"CNN as model observer in a liver lesion detection task for x-ray computed tomography: A phantom study,","volume":"45","author":"Kopp","journal-title":"Med. Phys."},{"issue":"2","key":"2026040902314272700_ref113","doi-asserted-by":"publisher","first-page":"938","DOI":"10.1137\/120882706","article-title":"A bilevel optimization approach for parameter learning in variational models,","volume":"6","author":"Kunisch","journal-title":"SIAM Journal on Imaging Sciences"},{"key":"2026040902314272700_ref114","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1017\/S0962492919000060","article-title":"Derivative-free optimization methods,","volume":"28","author":"Larson","journal-title":"Acta Numerica"},{"issue":"15","key":"2026040902314272700_ref115","first-page":"664","article-title":"A flexible framework for designing trainable priors with adaptive smoothing and game encoding,","volume":"33","author":"Lecouat","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"10","key":"2026040902314272700_ref116","doi-asserted-by":"publisher","first-page":"1588","DOI":"10.1109\/JPROC.2003.817882","article-title":"Overview of methods for image reconstruction from projections in emission computed tomography,","volume":"91","author":"Lewitt","journal-title":"Proc. IEEE"},{"issue":"11","key":"2026040902314272700_ref117","doi-asserted-by":"publisher","first-page":"3512","DOI":"10.1109\/TMI.2020.2998480","article-title":"Improved low-count quantitative PET reconstruction with an iterative neural network,","volume":"39","author":"Lim","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"2026040902314272700_ref118","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/jocn_a_01544","article-title":"Convolutional neural networks as a model of the visual system: Past, present, and future,","author":"Lindsay","year":"2020","journal-title":"Journal of Cognitive Neuroscience"},{"key":"2026040902314272700_ref119","author":"Liu","journal-title":"Learning multiscale convolutional dictionaries for image reconstruction"},{"key":"2026040902314272700_ref120","first-page":"1540","article-title":"Optimizing millions of hyperparameters by implicit differentiation,","author":"Lorraine","journal-title":"Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics"},{"issue":"1","key":"2026040902314272700_ref121","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/msp.2017.2760358","article-title":"Using deep neural networks for inverse problems in imaging: Beyond analytical methods,","volume":"35","author":"Lucas","journal-title":"IEEE Sig. Proc. Mag."},{"issue":"4","key":"2026040902314272700_ref122","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1109\/TPAMI.2011.156","article-title":"Task-driven dictionary learning,","volume":"34","author":"Mairal","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"2026040902314272700_ref123","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1137\/070697653","article-title":"Learning multiscale sparse representations for image and video restoration,","volume":"7","author":"Mairal","journal-title":"Multiscale Modeling & Simulation"},{"issue":"4","key":"2026040902314272700_ref124","doi-asserted-by":"publisher","first-page":"1064","DOI":"10.1109\/TMI.2019.2930338","article-title":"Comparison of objective image quality metrics to expert radiologists\u2019 scoring of diagnostic quality of MR images,","volume":"39","author":"Mason","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"3","key":"2026040902314272700_ref125","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1561\/2000000101","article-title":"Biomedical image reconstruction: From the foundations to deep neural networks,","volume":"13","author":"McCaxnn","year":"2019","journal-title":"Foundation and Trends in Signal Processing"},{"key":"2026040902314272700_ref126","article-title":"Supervised learning of sparsity-promoting regularizers for denoising,","author":"McCann","journal-title":"arXiv Computing Research Repository"},{"issue":"10","key":"2026040902314272700_ref127","doi-asserted-by":"publisher","first-page":"e339","DOI":"10.1002\/mp.12345","article-title":"Low-dose CT for the detection and classification of metastatic liver lesions: Results of the 2016 Low Dose CT Grand Challenge,","volume":"44","author":"McCollough","journal-title":"Med. Phys."},{"key":"2026040902314272700_ref128","first-page":"347","article-title":"Penalty method for inversion-free deep bilevel optimization,","author":"Mehra","year":"2021","journal-title":"Proceedings of The 13th Asian Conference on Machine Learning"},{"issue":"3","key":"2026040902314272700_ref129","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","article-title":"Making a \u201ccompletely blind","volume":"20","author":"Mittal","year":"2013","journal-title":"IEEE Signal Processing Letters"},{"issue":"2","key":"2026040902314272700_ref130","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/MSP.2020.3016905","article-title":"Algorithm unrolling: Interpretable, efficient deep learning for signal and image processing,","volume":"38","author":"Monga","year":"2021","journal-title":"IEEE Signal Processing Magazine"},{"key":"2026040902314272700_ref131","article-title":"Controlled random search improves sample mining and hyperparameter optimization,","author":"Muniraju","year":"2019","journal-title":"Thirty-Third AAAI Conference on Artificial Intelligence"},{"issue":"1","key":"2026040902314272700_ref132","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.acha.2012.03.006","article-title":"The cosparse analysis model and algorithms,","volume":"34","author":"Nam","year":"2013","journal-title":"Applied and Computational Harmonic Analysis"},{"issue":"2","key":"2026040902314272700_ref133","first-page":"372","article-title":"A method of solving a convex programming problem with convergence rate O(1\/k2),","volume":"27","author":"Nesterov","year":"1983","journal-title":"Soviet Math. Dokl."},{"key":"2026040902314272700_ref134","first-page":"9","article-title":"SARAH: A novel method for machine learning problems using stochastic recursive gradient,","author":"Nguyen","year":"2017","journal-title":"34th International Conference on Machine Learning"},{"issue":"2","key":"2026040902314272700_ref135","doi-asserted-by":"publisher","first-page":"399","DOI":"10.3934\/ipi.2007.1.399","article-title":"Model distortions in Bayesian MAP reconstruction,","volume":"1","author":"Nikolova","year":"2007","journal-title":"Inverse Problems & Imaging"},{"issue":"3-4","key":"2026040902314272700_ref136","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1561\/0600000033","article-title":"Structured learning and prediction in computer vision,","volume":"6","author":"Nowozin","year":"2011","journal-title":"Foundations and Trends\u00ae in Computer Graphics and Vision"},{"issue":"2","key":"2026040902314272700_ref137","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/s10851-016-0663-7","article-title":"Techniques for gradient-based bilevel optimization with non-smooth lower level problems,","volume":"56","author":"Ochs","year":"2016","journal-title":"Journal of Mathematical Imaging and Vision"},{"key":"2026040902314272700_ref138","first-page":"1465","article-title":"Sequential minimal eigenvalues - an approach to analysis dictionary learning,","author":"Ophir","year":"2011","journal-title":"19th European Signal Processing Conference"},{"key":"2026040902314272700_ref139","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804458","author":"Palomar","year":"2011","journal-title":"Convex optimization in signal processing and communications"},{"key":"2026040902314272700_ref140","first-page":"737","article-title":"Hyperparameter optimization with approximate gradient,","volume-title":"Proceedings International Conference on Machine Learning","author":"Pedregosa","year":"2016"},{"key":"2026040902314272700_ref141","author":"Petersen","journal-title":"The Matrix Cookbook"},{"issue":"5","key":"2026040902314272700_ref142","doi-asserted-by":"publisher","first-page":"896","DOI":"10.1109\/JSTSP.2011.2120592","article-title":"A review of adaptive image representations,","volume":"5","author":"Peyre","year":"2011","journal-title":"IEEE J. Sel. Top. Sig. Proc."},{"key":"2026040902314272700_ref143","article-title":"Learning analysis sparsity priors,","author":"Peyr\u00e9","year":"2011","journal-title":"IEEE Intl. Conf. on Sampling Theory and Appl. (SampTA)"},{"issue":"2","key":"2026040902314272700_ref144","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/TSP.2018.2883021","article-title":"Learning filter bank sparsifying trans-forms,","volume":"67","author":"Pfister","year":"2019","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"1","key":"2026040902314272700_ref145","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/321105.321114","article-title":"A technique for the numerical solution of certain integral equations of the first kind,","volume":"9","author":"Phillips","year":"1962","journal-title":"J. Assoc. Comput. Mach."},{"key":"2026040902314272700_ref146","article-title":"Smooth Bilevel Programming for Sparse Regularization,","volume-title":"35th Conference on Neural Information Processing Systems","author":"Poon","year":"2021"},{"issue":"16","key":"2026040902314272700_ref147","doi-asserted-by":"publisher","first-page":"4017","DOI":"10.1088\/0031-9155\/51\/16\/009","article-title":"Penalized maximum-likelihood image reconstruction for lesion detection,","volume":"51","author":"Qi","year":"2006","journal-title":"Phys. Med. Biol."},{"issue":"9","key":"2026040902314272700_ref148","doi-asserted-by":"publisher","first-page":"1540","DOI":"10.1109\/TIP.2008.2001404","article-title":"Monte-carlo sure: A black-box optimization of regularization parameters for general denoising algorithms,","volume":"17","author":"Ramani","year":"2008","journal-title":"IEEE Transactions on Image Processing"},{"key":"2026040902314272700_ref149","author":"Ramzi","year":"2021","journal-title":"SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit models"},{"issue":"5","key":"2026040902314272700_ref150","doi-asserted-by":"publisher","first-page":"1028","DOI":"10.1109\/TMI.2010.2090538","article-title":"MR image reconstruction from highly undersampled k-space data by dictionary learning,","volume":"30","author":"Ravishankar","year":"2011","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"1","key":"2026040902314272700_ref151","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/JPROC.2019.2936204","article-title":"Image reconstruction: From sparsity to data-adaptive methods and machine learning,","volume":"108","author":"Ravishankar","year":"2020","journal-title":"Proc. IEEE"},{"issue":"5","key":"2026040902314272700_ref152","doi-asserted-by":"publisher","first-page":"1072","DOI":"10.1109\/TSP.2012.2226449","article-title":"Learning sparsifying trans-forms,","volume":"61","author":"Ravishankar","year":"2013","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"3","key":"2026040902314272700_ref153","doi-asserted-by":"publisher","first-page":"035","DOI":"10.1117\/1.JMI.4.3.035501","article-title":"Structural similarity index family for image quality assessment in radiological images,","volume":"4","author":"Renieblas","year":"2017","journal-title":"J. Med. Im."},{"key":"2026040902314272700_ref154","author":"Roberts","year":"2021","journal-title":"Inexact DFO for Bilevel Learning: Dimension Question"},{"key":"2026040902314272700_ref155","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: Convolutional networks for biomedical image segmentation,","author":"Ronneberger","year":"2015","journal-title":"Medical Image Computing and Computer-Assisted Intervention"},{"key":"2026040902314272700_ref156","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1109\/CVPR.2005.160","article-title":"Fields of experts: A framework for learning image priors,","volume":"2","author":"Roth","year":"2005","journal-title":"2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905)"},{"issue":"1-4","key":"2026040902314272700_ref157","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/0167-2789(92)90242-F","article-title":"Nonlinear total variation based noise removal algorithm,","volume":"60","author":"Rudin","year":"1992","journal-title":"Physica D"},{"key":"2026040902314272700_ref158","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13264","article-title":"Deep learning in medical imaging and radiation therapy,","author":"Sahiner","year":"2018","journal-title":"Medical Physics"},{"key":"2026040902314272700_ref159","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1109\/CVPR.2009.5206774","article-title":"Learning optimized MAP estimates in continuously-valued MRF models,","author":"Samuel","year":"2009","journal-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition"},{"issue":"7","key":"2026040902314272700_ref160","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1109\/83.701163","article-title":"ML parameter estimation for Markov random fields, with applications to Bayesian tomography,","volume":"7","author":"Saquib","year":"1998","journal-title":"IEEE Trans. Im. Proc."},{"issue":"4","key":"2026040902314272700_ref161","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1287\/moor.26.4.851.10007","article-title":"How stringent is the linear independence assumption for mathematical programs with complementarity constraints?","volume":"26","author":"Scholtes","year":"2001","journal-title":"Mathematics of Operations Research"},{"issue":"9","key":"2026040902314272700_ref162","doi-asserted-by":"publisher","first-page":"4902","DOI":"10.1118\/1.3480985","article-title":"4D XCAT phantom for multimodality imaging research,","volume":"37","author":"Segars","year":"2010","journal-title":"Medical Physics"},{"key":"2026040902314272700_ref163","doi-asserted-by":"publisher","first-page":"1468","DOI":"10.1109\/ICASSP.2018.8461664","article-title":"Edge-based loss function for single image super-resolution,","volume-title":"Proc. IEEE Conf. Acoust. Speech Sig. Proc.","author":"Seif","year":"2018"},{"issue":"3","key":"2026040902314272700_ref164","doi-asserted-by":"publisher","first-page":"797","DOI":"10.4310\/CMS.2011.v9.n3.a7","article-title":"Infimal convolution regularizations with discrete \u21131-type functionals,","volume":"9","author":"Setzer","year":"2011","journal-title":"Comm. Math. Sci."},{"key":"2026040902314272700_ref165","first-page":"1723","article-title":"Truncated back-propagation for bilevel optimization,","volume-title":"Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics","author":"Shaban","year":"2019"},{"issue":"3","key":"2026040902314272700_ref166","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/TNS.1974.6499235","article-title":"The Fourier reconstruction of a head section,","volume":"21","author":"Shepp","year":"1974","journal-title":"IEEE Trans. Nuc. Sci."},{"key":"2026040902314272700_ref167","doi-asserted-by":"publisher","first-page":"4310","DOI":"10.1109\/TMI.2020.3017353","article-title":"Learning the sampling pattern for MRI,","volume-title":"IEEE Transactions on Medical Imaging","author":"Sherry","year":"2020"},{"key":"2026040902314272700_ref168","volume-title":"Modelbased deep learning","author":"Shlezinger","year":"2020"},{"issue":"1","key":"2026040902314272700_ref169","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning,","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"2026040902314272700_ref170","article-title":"Very deep convolutional networks for large-scale image recognition,","author":"Simonyan","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"2026040902314272700_ref171","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/17415977.2020.1864348","article-title":"Adaptative regularization parameter for poisson noise with a bilevel approach: Application to spectral computerized tomography,","author":"Sixou","year":"2020","journal-title":"Inverse Problems in Science and Engineering"},{"issue":"9","key":"2026040902314272700_ref172","doi-asserted-by":"publisher","first-page":"3961","DOI":"10.1002\/mp.14319","article-title":"Noise and spatial resolution properties of a commercially available deep learning-based CT reconstruction algorithm,","volume":"47","author":"Solomon","year":"2020","journal-title":"Med. Phys."},{"key":"2026040902314272700_ref173","article-title":"Training deep learning based denoisers without ground truth data,","volume":"31","author":"Soltanayev","year":"2018","journal-title":"Neural Information Processing Systems"},{"key":"2026040902314272700_ref174","first-page":"908","article-title":"Supervised sparse analysis and synthesis operators,","author":"Sprechmann","year":"2013","journal-title":"Neural Information Processing Systems"},{"issue":"6","key":"2026040902314272700_ref175","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176345632","article-title":"Estimation of the mean of a multivariate normal distribution,","volume":"9","author":"Stein","year":"1981","journal-title":"The Annals of Statistics"},{"issue":"1","key":"2026040902314272700_ref176","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1080\/02331887808801414","article-title":"Cross-validation: A review,","volume":"9","author":"Stone","year":"1978","journal-title":"Math Oper Stat Ser Stat."},{"key":"2026040902314272700_ref177","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/CVPR.2007.382979","article-title":"Learning gaussian conditional random fields for low-level vision,","author":"Tappen","year":"2007","journal-title":"2007 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"2026040902314272700_ref178","article-title":"Image & video quality assessment at LIVE.","author":"The University of Texas at Austin: Laboratory for Image and Video Engineering"},{"key":"2026040902314272700_ref179","author":"Thies","year":"2022","journal-title":"Learned Cone-Beam CT Reconstruction Using Neural Ordinary Differential Equations"},{"issue":"1","key":"2026040902314272700_ref180","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the Lasso,","volume":"58","author":"Tibshirani","year":"1996","journal-title":"Journal of the Royal Statistical Society: Series B (Methodological)"},{"issue":"3","key":"2026040902314272700_ref181","doi-asserted-by":"publisher","DOI":"10.1214\/11-AOS878","article-title":"The solution path of the generalized lasso,","volume":"39","author":"Tibshirani","year":"2011","journal-title":"The Annals of Statistics"},{"issue":"6","key":"2026040902314272700_ref182","doi-asserted-by":"publisher","first-page":"2146","DOI":"10.1109\/TSP.2005.847821","article-title":"Generalized smoothing splines and the optimal discretization of the Wiener filter,","volume":"53","author":"Unser","year":"2005","journal-title":"IEEE Trans. Sig. Proc."},{"key":"2026040902314272700_ref183","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1109\/GlobalSIP.2013.6737048","article-title":"Plug-and-Play priors for model based reconstruction,","author":"Venkatakrishnan","year":"2013","journal-title":"2013 IEEE Global Conference on Signal and Information Processing"},{"key":"2026040902314272700_ref184","doi-asserted-by":"publisher","first-page":"8914","DOI":"10.1109\/ACCESS.2016.2624938","article-title":"A perspective on deep imaging,","volume":"4","author":"Wang","year":"2016","journal-title":"IEEE Access"},{"issue":"4","key":"2026040902314272700_ref185","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity,","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Im. Proc."},{"key":"2026040902314272700_ref186","doi-asserted-by":"publisher","first-page":"1398","DOI":"10.1109\/ACSSC.2003.1292216","article-title":"Multiscale structural similarity for image quality assessment,","author":"Wang","year":"2003","journal-title":"The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003"},{"issue":"6","key":"2026040902314272700_ref187","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/MSP.2011.942471","article-title":"Reduced- and no-reference image quality assessment,","volume":"28","author":"Wang","year":"2011","journal-title":"IEEE Signal Processing Magazine"},{"issue":"1","key":"2026040902314272700_ref188","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/MSP.2019.2951469","article-title":"Transform learning for magnetic resonance image reconstruction: From model-based learning to building neural networks,","volume":"37","author":"Wen","year":"2020","journal-title":"IEEE Sig. Proc. Mag."},{"issue":"19","key":"2026040902314272700_ref189","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac0f9a","article-title":"Patient-specific hyperparameter learning for optimization-based CT image reconstruction,","volume":"66","author":"Xu","year":"2021","journal-title":"Physics in Medicine & Biology"},{"issue":"9","key":"2026040902314272700_ref190","doi-asserted-by":"publisher","first-page":"2341","DOI":"10.1109\/TSP.2013.2250968","article-title":"Constrained overcomplete analysis operator learning for cosparse signal modelling,","volume":"61","author":"Yaghoobi","year":"2013","journal-title":"IEEE Transactions on Signal Processing"},{"key":"2026040902314272700_ref191","first-page":"1470","article-title":"Analysis operator learning for overcomplete cosparse representations,","author":"Yaghoobi","year":"2011","journal-title":"presented at the 2011 19th European Signal Processing Conference"},{"key":"2026040902314272700_ref192","article-title":"Provably faster algorithms for bilevel optimization,","author":"Yang","year":"2021","journal-title":"35th Conference on Neural Information Processing Systems (NeurIPS 2021)"},{"issue":"2","key":"2026040902314272700_ref193","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1088\/0031-9155\/59\/2\/403","article-title":"Regularization design in penalized maximum-likelihood image reconstruction for lesion detection in 3D PET,","volume":"59","author":"Yang","year":"2014","journal-title":"Phys. Med. Biol."},{"issue":"2","key":"2026040902314272700_ref194","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1137\/17m1141771","article-title":"Deep convolutional framelets: A general deep learning framework for inverse problems,","volume":"11","author":"Ye","year":"2018","journal-title":"SIAM J. Imaging Sci."},{"issue":"12","key":"2026040902314272700_ref195","doi-asserted-by":"publisher","first-page":"B99","DOI":"10.1364\/JOSAA.24.000B99","article-title":"Analysis of observer performance in unknown-location tasks for tomographic image reconstruction,","volume":"24","author":"Yendiki","year":"2007","journal-title":"J. Opt. Soc. Am. A"},{"issue":"6","key":"2026040902314272700_ref196","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1002\/mrm.21245","article-title":"Joint image reconstruction and sensitivity estimation in SENSE (JSENSE),","volume":"57","author":"Ying","year":"2007","journal-title":"Mag. Res. Med."},{"key":"2026040902314272700_ref197","doi-asserted-by":"publisher","first-page":"41 839","DOI":"10.1109\/ACCESS.2018.2858196","article-title":"Structure-sensitive multi-scale deep neural network for low-dose CT denoising,","volume":"6","author":"You","year":"2018","journal-title":"IEEE Access"},{"key":"2026040902314272700_ref198","doi-asserted-by":"publisher","first-page":"19 767","DOI":"10.1109\/ACCESS.2020.2968726","article-title":"A bi-level nested sparse optimization for adaptive mechanical fault feature de-tection,","volume":"8","author":"Zhang","year":"2020","journal-title":"IEEE Access"},{"key":"2026040902314272700_ref199","doi-asserted-by":"publisher","first-page":"1477","DOI":"10.1109\/ICIP.2012.6467150","article-title":"A comprehensive evaluation of full reference image quality assessment algorithms,","author":"Zhang","year":"2012","journal-title":"2012 19th IEEE International Conference on Image Processing"},{"issue":"1","key":"2026040902314272700_ref200","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/TCSVT.2018.2886771","article-title":"Blind image quality assessment using a deep bilinear convolutional neural network,","volume":"30","author":"Zhang","year":"2020","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"3","key":"2026040902314272700_ref201","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.1109\/tip.2016.2623487","article-title":"Bilevel model-based discriminative dictionary learning for recognition,","volume":"26","author":"Zhou","year":"2017","journal-title":"IEEE Trans. Im. Proc."},{"key":"2026040902314272700_ref202","doi-asserted-by":"publisher","first-page":"10247","DOI":"10.1109\/CVPR.2019.01050","article-title":"Training deep learning based image denoisers from undersampled measurements without ground truth and without image prior,","author":"Zhussip","year":"2019","journal-title":"Proc. IEEE Conf. on Comp. Vision and Pattern Recognition"},{"issue":"2","key":"2026040902314272700_ref203","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net,","volume":"67","author":"Zou","year":"2005","journal-title":"J. Royal Stat. Soc. Ser. B"}],"container-title":["Foundations and Trends\u00ae in Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/ftsig\/article-pdf\/15\/2-3\/121\/11047145\/2000000111en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ftsig\/article-pdf\/15\/2-3\/121\/11047145\/2000000111en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:55:23Z","timestamp":1777488923000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ftsig\/article\/15\/2-3\/121\/1328600\/Bilevel-Methods-for-Image-Reconstruction"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,5]]},"references-count":203,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[2022,5,5]]}},"URL":"https:\/\/doi.org\/10.1561\/2000000111","relation":{},"ISSN":["1932-8346","1932-8354"],"issn-type":[{"value":"1932-8346","type":"print"},{"value":"1932-8354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,5]]}}}