{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:44:53Z","timestamp":1787323493002,"version":"3.56.0"},"reference-count":54,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"2","funder":[{"DOI":"10.13039\/100000964","name":"Arthritis National Research Foundation","doi-asserted-by":"publisher","award":["CRG\/2022\/00549"],"award-info":[{"award-number":["CRG\/2022\/00549"]}],"id":[{"id":"10.13039\/100000964","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]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>We present a data-assisted iterative regularization method for solving ill-posed inverse problems. The proposed approach, termed IRMGL+[Formula: see text], integrates classical iterative techniques with a data-driven regularization term realized through an iteratively updated graph Laplacian. Our method commences by computing a preliminary solution using any suitable reconstruction method, which then serves as the basis for constructing the initial graph Laplacian. The solution is subsequently refined through an iterative process, where the graph Laplacian is simultaneously recalibrated at each step to effectively capture the evolving structure of the solution. A key innovation of this work lies in the formulation of this iterative scheme and the rigorous justification of the classical discrepancy principle as a reliable early stopping criterion specifically tailored to the proposed method. Under standard assumptions, we establish stability and convergence results for the scheme when the discrepancy principle is applied. Furthermore, we demonstrate the robustness and effectiveness of our method through numerical experiments utilizing four distinct initial reconstructors [Formula: see text]: the adjoint operator (Adj), filtered back projection, total variation denoising, and standard Tikhonov regularization. It is observed that IRMGL + Adj demonstrates a distinct advantage over the other initializers, producing a robust and stable approximate solution directly from a basic initial reconstruction.<\/jats:p>","DOI":"10.1137\/25m1775506","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T08:01:41Z","timestamp":1775116901000},"page":"643-676","source":"Crossref","is-referenced-by-count":1,"title":["On the Convergence of the Iterative Regularization Method Assisted by the Graph Laplacian with Early Stopping"],"prefix":"10.1137","volume":"19","author":[{"given":"Harshit","family":"Bajpai","sequence":"first","affiliation":[{"name":"Department of Mathematics, Indian Institute of Technology Roorkee, Roorkee 247667, India."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaurav","family":"Mittal","sequence":"additional","affiliation":[{"name":"Defence Research and Development Organization, Near Metcalfe House, Delhi 110054, India."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6339-4647","authenticated-orcid":true,"given":"Ankik Kumar","family":"Giri","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Indian Institute of Technology Roorkee, Roorkee 247667, India."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2026,4,2]]},"reference":[{"key":"ref1","volume-title":"odlgroup\/odl:\u00a0ODL 0.7.0","author":"Adler J.","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03641-5_26"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492919000059"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/01630563.2020.1740734"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/abb61b"},{"key":"ref6","unstructured":"H. Bajpai, G. Mittal, and A. K. Giri, Hanke-Raus Heuristic Rule for Iteratively Regularized Stochastic Gradient Descent, preprint, arXiv:2412.02397, 2024."},{"key":"ref7","first-page":"153","volume":"33","author":"Bajpai H.","year":"2025","journal-title":"J. Inverse Ill-Posed Probl."},{"key":"ref8","author":"Barbano R.","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9467-7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1553\/etna_vol55s169"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-31975-4_14"},{"key":"ref12","unstructured":"D. Bianchi, F. Bossmann, W. Wang, and M. Liu, Improved Impedance Inversion by Deep Learning and Iterated Graph Laplacian, preprint, arXiv:2404.16324, 2024."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1137\/23M162750X"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"ref15","doi-asserted-by":"crossref","unstructured":"A. Buccini and M. Donatelli, Graph Laplacian in \\(l_2 \\text{-} l_q\\) regularization for image reconstruction, in 2021 International Conference on\u00a0Computer Science and Its Applications (ICCSA), IEEE, New York, 2021, pp. 29\u201338.","DOI":"10.1109\/ICCSA54496.2021.00015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/20\/5\/005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-016-0678-0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-1740-8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2022.102156"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/060669358"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1137\/070698592"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/21M140225X"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s002110050158"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718874"},{"key":"ref25","volume-title":"Fundamentals of Digital Image Processing","author":"Jain A. K.","year":"1989"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/abaa58"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1137\/24M1636617"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/19M1271798"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/22M1518542"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/24M1651721"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-00-01199-6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1515\/9783110208276"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719277"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-81459-5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/140967982"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/ab6d57"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-009-9320-2"},{"key":"ref38","first-page":"8516","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"31","author":"Lunz S.","year":"2018"},{"key":"ref39","doi-asserted-by":"crossref","unstructured":"T. Meinhardt, M. M\u00f6ller, 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 (ICCV), IEEE, New York, 2017, pp. 1781\u20131790.","DOI":"10.1109\/ICCV.2017.198"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.jco.2024.101897"},{"key":"ref41","first-page":"510","volume":"167","author":"Morozov V.","year":"1966","journal-title":"Dokl. Akad. Nauk SSSR"},{"key":"ref42","volume-title":"SIAM","author":"Natterer F.","year":"2001"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827598341384"},{"key":"ref44","doi-asserted-by":"crossref","unstructured":"D. Obmann, L. Nguyen, J. Schwab, and M. Haltmeier, Sparse Anett for solving inverse problems with deep learning, in 2020 IEEE 17th International Symposium on Biomedical Imaging Workshops, IEEE, New York, 2020, pp. 1\u20134.","DOI":"10.1109\/ISBIWorkshops50223.2020.9153362"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88690-7_5"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3934\/ipi.2011.5.511"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1137\/16M1102884"},{"key":"ref48","first-page":"234","volume-title":"MICCAI 2015","author":"Ronneberger O.","year":"2015"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s002459900081"},{"key":"ref50","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-69277-7","volume-title":"Variational Methods in Imaging","volume":"167","author":"Scherzer O.","year":"2009"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898717570"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref53","series-title":"Trans. Mach. Learn. Res.","volume-title":"Early stopping for deep image prior","author":"Wang H.","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1137\/090746379"}],"container-title":["SIAM Journal on Imaging Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/25M1775506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:05:23Z","timestamp":1787321123000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/25M1775506"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,2]]},"references-count":54,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1137\/25M1775506"],"URL":"https:\/\/doi.org\/10.1137\/25m1775506","relation":{},"ISSN":["1936-4954"],"issn-type":[{"value":"1936-4954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,2]]}}}