{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:33:52Z","timestamp":1787322832646,"version":"build-2736575974"},"reference-count":52,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"1","funder":[{"name":"Hong Kong Research Grants Council","award":["15303021"],"award-info":[{"award-number":["15303021"]}]},{"DOI":"10.13039\/501100004853","name":"Chinese University of Hong Kong","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004853","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004377","name":"Hong Kong Polytechnic University","doi-asserted-by":"publisher","award":["P0038888"],"award-info":[{"award-number":["P0038888"]}],"id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T000864\/1"],"award-info":[{"award-number":["EP\/T000864\/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":[[2024,3,31]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>In this work, we develop a novel approach using deep neural networks (DNNs) to reconstruct the conductivity distribution in elliptic problems from one measurement of the solution over the whole domain. The approach is based on a mixed reformulation of the governing equation and utilizes the standard least-squares objective, with DNNs as ansatz functions to approximate the conductivity and flux simultaneously. We provide a thorough analysis of the DNN approximations of the conductivity for both continuous and empirical losses, including rigorous error estimates that are explicit in terms of the noise level, various penalty parameters, and neural network architectural parameters (depth, width, and parameter bounds). We also provide multiple numerical experiments in two dimensions and multidimensions to illustrate distinct features of the approach, e.g., excellent stability with respect to data noise and capability of solving high-dimensional problems.<\/jats:p>","DOI":"10.1137\/23m1562536","type":"journal-article","created":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T04:32:34Z","timestamp":1705984354000},"page":"147-187","source":"Crossref","is-referenced-by-count":7,"title":["Conductivity Imaging from Internal Measurements with Mixed Least-Squares Deep Neural Networks"],"prefix":"10.1137","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3775-9155","authenticated-orcid":true,"given":"Bangti","family":"Jin","sequence":"first","affiliation":[{"name":"Department of Mathematics, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong, People\u2019s Republic of China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiyao","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University College London, London WC1E 6BT, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qimeng","family":"Quan","sequence":"additional","affiliation":[{"name":"Department of Mathematics, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong, People\u2019s Republic of China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3439-0313","authenticated-orcid":true,"given":"Zhi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics, Hong Kong Polytechnic University, Kowloon, Hong Kong, People\u2019s Republic of China."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2024,1,23]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1137\/0331058"},{"key":"ref2","volume-title":"Sobolev Spaces","author":"Adams R. A.","year":"2003","edition":"2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/28\/9\/095006"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF01790543"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511624216"},{"key":"ref6","series-title":"Mathematical Sciences Research Institute Publications 60","first-page":"325","volume-title":"Inverse Problems and Applications: Inside Out. II","author":"Bal G.","year":"2013"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/abb447"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/20M1332827"},{"key":"ref9","first-page":"463","volume":"3","author":"Bartlett P. L.","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/16M1094476"},{"key":"ref11","author":"Cen S.","journal-title":"IMA J. Numer. Anal."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997318602"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1090\/S0273-0979-01-00923-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/28\/11\/115015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6544\/ac337f"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s40304-018-0127-z"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-1740-8"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1983-0689469-3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1029\/WR009i005p01397"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.11.010"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/20M1367350"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1515\/jnum-2012-0013"},{"key":"ref24","volume-title":"Inverse Problems: Tikhonov Theory and Algorithms","author":"Ito K.","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/ac6d03"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/20M134383X"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/13\/4\/009"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/18M1222399"},{"key":"ref29","unstructured":"D. P. Kingma  and \nJ. Ba  , Adam: A method for stochastic optimization, in 3rd International Conference for Learning Representations, San Diego, CA, 2015."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1051\/m2an\/1988220101191"},{"key":"ref31","unstructured":"Y. Lu , \nJ. Lu , and \nM. Wang  , A priori generalization analysis of the deep Ritz method for solving high dimensional elliptic partial differential equations, in Conference on Learning Theory, PMLR, jmlr.org, 2021, pp. 3196\u20133241."},{"key":"ref32","volume-title":"Foundations of Machine Learning","author":"Mohri M.","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/S0898-1221(98)00001-7"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2021.110414"},{"key":"ref35","unstructured":"A. Pokkunuru , \nP. Rooshenas , \nT. Strauss , \nA. Abhishek , and \nT. Khan  , Improved training of physics-informed neural networks using energy-based priors: A study on electrical impedance tomography, in International Conference on Learning Representation, openreview.net, 2023."},{"key":"ref36","unstructured":"N. Rahaman , \nA. Baratin , \nD. Arpit , \nF. Draxler , \nM. Lin , \nF. Hamprecht , \nY. Bengio , and \nA. Courville  , On the spectral bias of neural networks, in Proceedings of the 36th International Conference on Machine Learning, PMLR 97, jmlr.org, 2019, pp. 5301\u20135310."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1137\/0141016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(92)90242-F"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1137\/18M1222600"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2023.112084"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/ace9d4"},{"key":"ref44","doi-asserted-by":"crossref","unstructured":"D. Ulyanov , \nA. Vedaldi , and \nV. Lempitsky  , Deep image prior, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), https:\/\/openaccess.thecvf.com, 2018, pp. 9446\u20139454.","DOI":"10.1109\/CVPR.2018.00984"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/21\/1\/012"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3934\/dcdsb.2010.14.1641"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/28\/8\/084008"},{"key":"ref48","unstructured":"M. M. Wolf  , Mathematical Foundations of Supervised Learning, Lecture notes, https:\/\/www-m5.ma.tum.de\/foswiki\/pub\/M5\/Allgemeines\/MA4801_2021S\/ML.pdf, 2021."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2021.110938"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1029\/WR022i002p00095"},{"key":"ref51","unstructured":"T. Yu  and \nH. Zhu  , Hyper-Parameter Optimization: A Review of Algorithms and Applications, preprint, arXiv:2003.05689, 2020."},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1015-3"}],"container-title":["SIAM Journal on Imaging Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/23M1562536","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T13:28:09Z","timestamp":1787318889000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/23M1562536"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,23]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,3,31]]}},"alternative-id":["10.1137\/23M1562536"],"URL":"https:\/\/doi.org\/10.1137\/23m1562536","relation":{},"ISSN":["1936-4954"],"issn-type":[{"value":"1936-4954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,23]]}}}