{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:02:46Z","timestamp":1787320966305,"version":"build-2736575974"},"reference-count":41,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"1","funder":[{"DOI":"10.13039\/501100007241","name":"Universit\u00e9 Paris-Saclay","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007241","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012107","name":"Fondation CentraleSup\u00e9lec","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012107","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000332","name":"Royal Society of Edinburgh","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000332","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/X028860\/1"],"award-info":[{"award-number":["EP\/X028860\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CVN"},{"DOI":"10.13039\/100012950","name":"Institut national de recherche en informatique et en automatique","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Imaging Sci."],"published-print":{"date-parts":[[2025,3,31]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>This article introduces a novel approach to learning monotone neural networks (NNs) through a newly defined penalization loss. The proposed method is particularly effective in solving classes of variational problems, specifically monotone inclusion problems, commonly encountered in image processing tasks. The forward-backward-forward (FBF) algorithm is employed to address these problems, offering a solution even when the Lipschitz constant of the NN is unknown. Notably, the FBF algorithm provides convergence guarantees under the condition that the learned operator is monotone. Building on plug-and-play methodologies, our objective is to apply these newly learned operators to solving nonlinear inverse problems. To achieve this, we initially formulate the problem as a variational inclusion problem. Subsequently, we train a monotone NN to approximate an operator that may not inherently be monotone. Leveraging the FBF algorithm, we then show simulation examples where the nonlinear inverse problem is successfully solved.<\/jats:p>","DOI":"10.1137\/24m1643347","type":"journal-article","created":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T04:02:25Z","timestamp":1743048145000},"page":"735-764","source":"Crossref","is-referenced-by-count":7,"title":["Learning Truly Monotone Operators with Applications to Nonlinear Inverse Problems"],"prefix":"10.1137","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1646-8516","authenticated-orcid":true,"given":"Younes","family":"Belkouchi","sequence":"first","affiliation":[{"name":"CentraleSupelec, Inria, Universit\u00e9 Paris-Saclay, Gif-sur-Yvette 91190, France."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5943-8061","authenticated-orcid":true,"given":"Jean-Christophe","family":"Pesquet","sequence":"additional","affiliation":[{"name":"CentraleSupelec, Inria, Universit\u00e9 Paris-Saclay, Gif-sur-Yvette 91190, France."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6296-6957","authenticated-orcid":true,"given":"Audrey","family":"Repetti","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Sciences and School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh EH14 4AS, UK, and Maxwell Institute for Mathematical Sciences, Bayes Centre, Edinburgh EH9 3FD, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2179-3498","authenticated-orcid":true,"given":"Hugues","family":"Talbot","sequence":"additional","affiliation":[{"name":"CentraleSupelec, Inria, Universit\u00e9 Paris-Saclay, Gif-sur-Yvette 91190, France."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2025,3,27]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"16836","DOI":"10.52202\/068431-1225","volume-title":"Advances in Neural Information Processing Systems 35","author":"Ahn B.","year":"2022"},{"key":"ref2","doi-asserted-by":"crossref","unstructured":"A. H. Al-Shabili, X. Xu, I. Selesnick, and U. S. Kamilov, Bregman plug-and-play priors, in Proceedings of the International Conference on Image Processing, IEEE, New York, 2022, pp. 241\u2013245.","DOI":"10.1109\/ICIP46576.2022.9897933"},{"key":"ref3","doi-asserted-by":"crossref","unstructured":"M. S. C. Almeida and M. A. T. Figueiredo, Blind image deblurring with unknown boundaries using the alternating direction method of multipliers, in Proceedings of the International Conference on Image Processing, IEEE, New York, 2013, pp. 586\u2013590.","DOI":"10.1109\/ICIP.2013.6738121"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48311-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492918000016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01501-5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1137\/22M1541630"},{"key":"ref8","doi-asserted-by":"crossref","unstructured":"C. A. Bouman and G. T. Buzzard, Generative Plug and Play: Posterior Sampling for Inverse Problems, in 2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton), Monticello, IL, 2023, pp. 1\u20137, https:\/\/doi.org\/10.1109\/Allerton58177.2023.10313413.","DOI":"10.1109\/Allerton58177.2023.10313413"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/wics.1427"},{"key":"ref10","doi-asserted-by":"crossref","unstructured":"S. Chaudhari, S. Pranav, and J. M. Moura, Learning gradients of convex functions with Monotone gradient networks, in Proceedings of the ICASSP IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, New York, 2023, pp. 1\u20135.","DOI":"10.1109\/ICASSP49357.2023.10097266"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1137\/20M1337168"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3934\/ipi.2023014"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2007.910264"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9569-8_10"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/19M1272780"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3069677"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/21M1420368"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2044803"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/22M1490843"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1093\/pnasnexus\/pgae164"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5201\/ipol.2012.g-tvd"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2021.3118944"},{"key":"ref23","author":"Hurault S.","year":"2023","journal-title":"in Advances in Neural Information Processing Systems 36 (NeurIPS 2023)"},{"key":"ref24","volume-title":"Gradient Step Denoiser for Convergent Plug-and-Play","author":"Hurault S.","year":"2022"},{"key":"ref25","unstructured":"S. Hurault, A. Leclaire, and N. Papadakis, Proximal denoiser for convergent plug-and-play optimization with nonconvex regularization, in International Conference on Machine Learning, PMLR, 2022, pp. 9483\u20139505."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2022.3199595"},{"key":"ref27","volume":"29","author":"Kingma D. P.","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref28","unstructured":"J. Kruse, L. Ardizzone, C. Rother, and U. K\u00f6the, Benchmarking Invertible Architectures on Inverse Problems, preprint, arXiv:2101.10763, 2021."},{"key":"ref29","volume-title":"Linear and Nonlinear Programming","volume":"2","author":"Luenberger D. G.","year":"1984"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3635159"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/20M1387961"},{"key":"ref32","unstructured":"D. J. Rezende and S. Mohamed, Variational Inference with Normalizing Flows, preprint, https:\/\/arxiv.org\/abs\/1505.05770, 2016."},{"key":"ref33","unstructured":"D. Runje and S. M. Shankaranarayana, Constrained monotonic neural networks, in International Conference on Machine Learning, PMLR, 2023, pp. 29338\u201329353."},{"key":"ref34","unstructured":"E. Ryu, J. Liu, S. Wang, X. Chen, Z. Wang, and W. Yin, Plug-and-play methods provably converge with properly trained denoisers, in International Conference on Machine Learning, PMLR, 2019, pp. 5546\u20135557."},{"key":"ref35","unstructured":"R. M. Schmidt, F. Schneider, and P. Hennig, Descending through a crowded valley-benchmarking deep learning optimizers, in International Conference on Machine Learning, PMLR, 2021, pp. 9367\u20139376."},{"key":"ref36","unstructured":"M. Tang and A. Repetti, A Data-Driven Approach for Bayesian Uncertainty Quantification in Imaging, preprint, arXiv:2304.11200, 2023."},{"key":"ref37","doi-asserted-by":"crossref","unstructured":"M. Terris, A. Repetti, J.C. Pesquet, and Y. Wiaux, Building firmly nonexpansive convolutional neural networks, in Proceedings of the ICASSP IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, New York, 2020, pp. 8658\u20138662.","DOI":"10.1109\/ICASSP40776.2020.9054731"},{"key":"ref38","doi-asserted-by":"crossref","unstructured":"M. Terris, A. Repetti, J.C. Pesquet, and Y. Wiaux, Enhanced convergent PNP algorithms For image restoration, in Proceedings of the International Conference on Image Processing, IEEE, New York, 2021, pp. 1684\u20131688.","DOI":"10.1109\/ICIP42928.2021.9506226"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012998338806"},{"key":"ref40","volume":"32","author":"Wang W.","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2802944"}],"container-title":["SIAM Journal on Imaging Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/24M1643347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T13:03:07Z","timestamp":1787317387000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/24M1643347"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,27]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,3,31]]}},"alternative-id":["10.1137\/24M1643347"],"URL":"https:\/\/doi.org\/10.1137\/24m1643347","relation":{},"ISSN":["1936-4954"],"issn-type":[{"value":"1936-4954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,27]]}}}