{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T09:48:27Z","timestamp":1776937707217,"version":"3.51.4"},"reference-count":67,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"2","funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/S026045\/1"],"award-info":[{"award-number":["EP\/S026045\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T026693\/1"],"award-info":[{"award-number":["EP\/T026693\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/V026259\/1"],"award-info":[{"award-number":["EP\/V026259\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Imaging Sci."],"published-print":{"date-parts":[[2026,6,30]]},"DOI":"10.1137\/25m1751839","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T09:01:26Z","timestamp":1776934886000},"page":"782-806","source":"Crossref","is-referenced-by-count":0,"title":["A Primal-Dual Algorithm for Image Reconstruction with Input-Convex Neural Network Regularizers"],"prefix":"10.1137","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8523-353X","authenticated-orcid":true,"given":"Matthias J.","family":"Ehrhardt","sequence":"first","affiliation":[{"name":"Department of Mathematical Sciences, University of Bath, Bath BA2 7AY, UK."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subhadip","family":"Mukherjee","sequence":"additional","affiliation":[{"name":"Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology (IIT), Kharagpur, India."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7267-778X","authenticated-orcid":true,"given":"Hok Shing","family":"Wong","sequence":"additional","affiliation":[{"name":"Department of Mathematical Sciences, University of Bath, Bath BA2 7AY, UK."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"351","published-online":{"date-parts":[[2026,4,23]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2799231"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.881199"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/acce5e"},{"key":"ref4","unstructured":"B. Amos, L. Xu, and J. Z. Kolter, Input convex neural networks, in International Conference on Machine Learning, PMLR, 2017, pp. 146\u2013155."},{"key":"ref5","unstructured":"L. Ardizzone, J. Kruse, S. Wirkert, D. Rahner, E. W. Pellegrini, R. S. Klessen, L. Maier-Hein, C. Rother, and U. K\u00f6the, Analyzing inverse problems with invertible neural networks, in Proceedings of 2019 Conference Blind Submission, ICLR, 2018."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492919000059"},{"key":"ref7","unstructured":"A. Askari, G. Negiar, R. Sambharya, and L. E. Ghaoui, Lifted Neural Networks, Technical Report No. UCB\/EECS-2021-218, University of California, Berkeley, 2018."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/080716542"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015187"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492918000016"},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"J. Bolte, E. Pauwels, and S. Vaiter, One-step differentiation of iterative algorithms, in Proceedings of Thirty-seventh Conference on Neural Information Processing Systems, 2023.","DOI":"10.52202\/075280-3371"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref13","series-title":"Lecture notes for EE392o","volume-title":"Subgradient Methods","author":"Boyd S.","year":"2003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/090769521"},{"key":"ref15","series-title":"Radon Series on Computational and Applied Mathematics 18","first-page":"252","volume-title":"Variational Methods: In Imaging and Geometric Control","author":"Calatroni L.","year":"2017"},{"key":"ref16","first-page":"10","volume-title":"Artificial Intelligence and Statistics, PMLR","author":"Carreira-Perpinan M.","year":"2014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/17M1134834"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-010-0251-1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0957-3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2715284"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2299065"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-014-0664-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1561\/2000000111"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.20042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/09076934X"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/18M1168480"},{"key":"ref27","doi-asserted-by":"crossref","unstructured":"S. W. Fung, H. Heaton, Q. Li, D. McKenzie, S. Osher, and W. Yin, JFB: Jacobian-free backpropagation for implicit networks, in Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36, AAAI, Washington, DC, 2022, pp. 6648\u20136656.","DOI":"10.1609\/aaai.v36i6.20619"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2023.3306100"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/23M1565243"},{"key":"ref30","unstructured":"R. Grazzi, L. Franceschi, M. Pontil, and S. Salzo, On the iteration complexity of hypergradient computation, in International Conference on Machine Learning, PMLR, 2020, pp. 3748\u20133758."},{"key":"ref31","doi-asserted-by":"crossref","unstructured":"J. Hertrich, H. S. Wong, A. Denker, S. Ducotterd, Z. Fang, M. Haltmeier, \u017d. Kereta, E. Kobler, O. Leong, M. S. Salehi, C.B. Sch\u00f6nlieb, J. Schwab, Z. Shumaylov, J. Sulam, G. Sh\u00e2ma Wache, M. Zach, Y. Zhang, M. J. Ehrhardt, and S. Neumayer, Learning Regularization Functionals for Inverse Problems: A Comparative Study, preprint, arXiv:2510.01755, 2025.","DOI":"10.1016\/bs.hna.2026.04.001"},{"key":"ref32","unstructured":"K. Ji, J. Yang, and Y. Liang, Bilevel optimization: Convergence analysis and enhanced design, in International Conference on Machine Learning, PMLR, 2021, pp. 4882\u20134892."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2713099"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12344"},{"key":"ref35","doi-asserted-by":"crossref","unstructured":"T. Karras, S. Laine, and T. Aila, A style-based generator architecture for generative adversarial networks, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, Washington, DC, 2019, pp. 4401\u20134410.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref36","unstructured":"D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, in Proceedings 3rd International Conference on Learning Representations, ICLR, San Diego, CA, 2015."},{"key":"ref37","doi-asserted-by":"crossref","unstructured":"E. Kobler, A. Effland, K. Kunisch, and T. Pock, Total deep variation for linear inverse problems, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, Washington, DC, 2020, pp. 7549\u20137558.","DOI":"10.1109\/CVPR42600.2020.00757"},{"key":"ref38","doi-asserted-by":"crossref","unstructured":"E. Kobler, T. Klatzer, K. Hammernik, and T. Pock, Variational networks: Connecting variational methods and deep learning, in Pattern Recognition, V. Roth and T. Vetter, eds. Springer-Verlag, Berlin, 2017, pp. 281\u2013293.","DOI":"10.1007\/978-3-319-66709-6_23"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1137\/120882706"},{"key":"ref40","first-page":"379","volume":"28","author":"Li H.","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/ab6d57"},{"key":"ref42","doi-asserted-by":"crossref","unstructured":"J. Li, C. Fang, and Z. Lin, Lifted proximal operator machines, in Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, AAAI, Washington, DC, 2019, pp. 4181\u20134188.","DOI":"10.1609\/aaai.v33i01.33014181"},{"key":"ref43","first-page":"8516","volume":"31","author":"Lunz S.","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref44","first-page":"3759","volume":"43","author":"McCollough C.","year":"2016","journal-title":"Med. Phys."},{"key":"ref45","unstructured":"S. Mehmood and P. Ochs, Automatic differentiation of some first-order methods in parametric optimization, in International Conference on Artificial Intelligence and Statistics, PMLR, 2020, pp. 1584\u20131594."},{"key":"ref46","doi-asserted-by":"crossref","unstructured":"T. Meinhardt, M. Moller, C. Hazirbas, and D. Cremers, Learning proximal operators: Using denoising networks for regularizing inverse imaging problems, in Proceedings of the IEEE International Conference on Computer Vision, IEEE Computer Society, Washington, DC, 2017, pp. 1781\u20131790.","DOI":"10.1109\/ICCV.2017.198"},{"key":"ref47","doi-asserted-by":"crossref","unstructured":"S. Mukherjee, S. Dittmer, Z. Shumaylov, S. Lunz, O. \u00d6ktem, and C.B. Sch\u00f6nlieb, Data-driven convex regularizers for inverse problems, in Proceedings ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, pp. 13386\u201313390.","DOI":"10.1109\/ICASSP48485.2024.10447719"},{"key":"ref48","first-page":"543","volume":"269","author":"Nesterov Y.","year":"1983","journal-title":"Dokl.\u00a0Akad.\u00a0Nauk SSSR"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-016-0663-7"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2991563"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1561\/2400000003"},{"key":"ref52","doi-asserted-by":"crossref","unstructured":"T. Pock and A. Chambolle, Diagonal preconditioning for first order primal-dual algorithms in convex optimization, in 2011 International Conference on Computer Vision, IEEE Computer Society, Washington, DC, 2011, pp. 1762\u20131769.","DOI":"10.1109\/ICCV.2011.6126441"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(64)90137-5"},{"key":"ref54","doi-asserted-by":"crossref","unstructured":"J. Prost, A. Houdard, A. Almansa, and N. Papadakis, Learning local regularization for variational image restoration, in International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2021), Springer-Verlag, Berlin, 2021, pp. 358\u2013370.","DOI":"10.1007\/978-3-030-75549-2_29"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0197-6"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(92)90242-F"},{"key":"ref57","doi-asserted-by":"crossref","unstructured":"K. G. Samuel and M. F. Tappen, Learning optimized map estimates in continuously-valued MRF models, in 2009 IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, Washington, DC, 2009, pp. 477\u2013484.","DOI":"10.1109\/CVPR.2009.5206774"},{"key":"ref58","series-title":"Applied Mathematical Sciences 167","volume-title":"Variational Methods in Imaging","author":"Scherzer O.","year":"2009"},{"key":"ref59","unstructured":"G. Taylor, R. Burmeister, Z. Xu, B. Singh, A. Patel, and T. Goldstein, Training neural networks without gradients: A scalable ADMM approach, in International Conference on Machine Learning, PMLR, 2016, pp. 2722\u20132731."},{"key":"ref60","first-page":"1","volume":"24","author":"Wang X.","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2012.2195669"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-018-0680-3"},{"key":"ref63","unstructured":"Y. Yang, J. Sun, H. Li, and Z. Xu, Deep ADMM-Net for compressive sensing MRI, in NIPS\u201916: Proceedings of the 30th International Conference on Neural Information Processing Systems, Curran Associates, Inc., Red Hook, NY, 2016, pp. 10\u201318."},{"key":"ref64","unstructured":"Z. Zhang and M. Brand, Convergent block coordinate descent for training Tikhonov regularized deep neural networks, in NIPS\u201917: Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017, pp. 1719\u20131728."},{"key":"ref65","volume":"34","author":"Zhu M.","year":"2008","journal-title":"UCLA CAM Report"},{"key":"ref66","doi-asserted-by":"crossref","unstructured":"D. Zoran and Y. Weiss, From learning models of natural image patches to whole image restoration, in 2011 International Conference on Computer Vision, IEEE Computer Society, Washington, DC, 2011, pp. 479\u2013486.","DOI":"10.1109\/ICCV.2011.6126278"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01547"}],"container-title":["SIAM Journal on Imaging Sciences"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T09:01:50Z","timestamp":1776934910000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/25M1751839"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,23]]},"references-count":67,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1137\/25M1751839"],"URL":"https:\/\/doi.org\/10.1137\/25m1751839","relation":{},"ISSN":["1936-4954"],"issn-type":[{"value":"1936-4954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,23]]}}}