{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T05:00:20Z","timestamp":1785387620453,"version":"3.55.0"},"reference-count":85,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,7,30]],"date-time":"2027-07-30T00:00:00Z","timestamp":1816905600000},"content-version":"am","delay-in-days":241,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100000005","name":"US Department of War","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"US Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006132","name":"US Department of Energy Office of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006132","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007287","name":"California Institute of Technology Resnick Sustainability Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007287","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Computational Physics"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.jcp.2026.115240","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T16:14:52Z","timestamp":1785168892000},"page":"115240","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Operator learning at machine precision"],"prefix":"10.1016","volume":"566","author":[{"given":"Aras","family":"Bacho","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aleksei G.","family":"Sorokin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianjin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Th\u00e9o","family":"Bourdais","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edoardo","family":"Calvello","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthieu","family":"Darcy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander W.","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bamdad","family":"Hosseini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5677-1600","authenticated-orcid":false,"given":"Houman","family":"Owhadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jcp.2026.115240_bib0001","series-title":"A mathematical guide to operator learning","first-page":"83","volume":"vol. 25","author":"Boull\u00e9","year":"2024"},{"key":"10.1016\/j.jcp.2026.115240_bib0002","first-page":"419","article-title":"Operator learning: algorithms and analysis","volume":"25","author":"Kovachki","year":"2024","journal-title":"Handb. Numer. Anal."},{"key":"10.1016\/j.jcp.2026.115240_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.jcp.2023.112549","article-title":"Kernel methods are competitive for operator learning","volume":"496","author":"Batlle","year":"2024","journal-title":"J. Comput. Phys."},{"issue":"6","key":"10.1016\/j.jcp.2026.115240_bib0004","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1038\/s42254-021-00314-5","article-title":"Physics-informed machine learning","volume":"3","author":"Karniadakis","year":"2021","journal-title":"Nat. Rev. Phys."},{"issue":"15","key":"10.1016\/j.jcp.2026.115240_bib0005","doi-asserted-by":"crossref","first-page":"3932","DOI":"10.1073\/pnas.1517384113","article-title":"Discovering governing equations from data by sparse identification of nonlinear dynamical systems","volume":"113","author":"Brunton","year":"2016","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"2","key":"10.1016\/j.jcp.2026.115240_bib0006","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1137\/18M1191944","article-title":"Data-driven identification of parametric partial differential equations","volume":"18","author":"Rudy","year":"2019","journal-title":"SIAM J. Appl. Dyn. Syst."},{"key":"10.1016\/j.jcp.2026.115240_bib0007","unstructured":"Y. Jalalian, J.F. Osorio Ramirez, A. Hsu, B. Hosseini, H. Owhadi, Data-efficient kernel methods for learning differential equations and their solution operators: Algorithms and error analysis, 2025. arXiv preprint arXiv: 2503.01036."},{"key":"10.1016\/j.jcp.2026.115240_bib0008","series-title":"ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"The uniqueness problem of physical law learning","author":"Scholl","year":"2023"},{"key":"10.1016\/j.jcp.2026.115240_bib0009","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1007\/s10994-026-07068-0","article-title":"Symbolic recovery of differential equations: The identifiability problem","volume":"115","author":"Scholl","year":"2026","journal-title":"Mach. Learn."},{"issue":"3","key":"10.1016\/j.jcp.2026.115240_bib0010","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1007\/s10915-022-01939-z","article-title":"Scientific machine learning through physics\u2013informed neural networks: Where we are and what\u2019s next","volume":"92","author":"Cuomo","year":"2022","journal-title":"J. Sci. Comput."},{"key":"10.1016\/j.jcp.2026.115240_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.jcp.2021.110668","article-title":"Solving and learning nonlinear pdes with gaussian processes","volume":"447","author":"Chen","year":"2021","journal-title":"J. Comput. Phys."},{"key":"10.1016\/j.jcp.2026.115240_bib0012","series-title":"Advances in Neural Information Processing Systems","article-title":"Convolutional neural operators","author":"Bartolucci","year":"2024"},{"key":"10.1016\/j.jcp.2026.115240_bib0013","series-title":"Proceedings of Machine Learning Research","first-page":"25105","article-title":"Neural inverse operators for solving PDE inverse problems","volume":"Vol. 202","author":"Molinaro","year":"2023"},{"issue":"3","key":"10.1016\/j.jcp.2026.115240_bib0014","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1038\/s42256-021-00302-5","article-title":"Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators","volume":"3","author":"Lu","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.jcp.2026.115240_bib0015","series-title":"International Conference on Learning Representations","article-title":"Fourier neural operator for parametric partial differential equations","author":"Li","year":"2021"},{"key":"10.1016\/j.jcp.2026.115240_bib0016","series-title":"Machine Learning in Modeling and Simulation: Methods and Applications","first-page":"219","article-title":"Physics-informed deep neural operator networks","author":"Goswami","year":"2023"},{"key":"10.1016\/j.jcp.2026.115240_bib0017","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1007\/s10958-006-0066-1","article-title":"Newton-kantorovich method and its global convergence","volume":"133","author":"Polyak","year":"2006","journal-title":"J. Math. Sci."},{"issue":"89","key":"10.1016\/j.jcp.2026.115240_bib0018","first-page":"1","article-title":"Neural operator: learning maps between function spaces with applications to pdes","volume":"24","author":"Kovachki","year":"2023","journal-title":"J. Mach. Learn. Res."},{"issue":"20","key":"10.1016\/j.jcp.2026.115240_bib0019","first-page":"1","article-title":"Operator-valued kernels for learning from functional response data","volume":"17","author":"Kadri","year":"2016","journal-title":"J. Mach. Learn. Res."},{"issue":"5","key":"10.1016\/j.jcp.2026.115240_bib0020","doi-asserted-by":"crossref","first-page":"A3212","DOI":"10.1137\/20M133957X","article-title":"The random feature model for input-output maps between banach spaces","volume":"43","author":"Nelsen","year":"2021","journal-title":"SIAM J. Sci. Comput."},{"key":"10.1016\/j.jcp.2026.115240_bib0021","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.jcp.2019.03.040","article-title":"Kernel flows: from learning kernels from data into the abyss","volume":"389","author":"Owhadi","year":"2019","journal-title":"J. Comput. Phys."},{"key":"10.1016\/j.jcp.2026.115240_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.physd.2022.133592","article-title":"Do ideas have shape? Idea registration as the continuous limit of artificial neural networks","volume":"444","author":"Owhadi","year":"2023","journal-title":"Phys. D"},{"key":"10.1016\/j.jcp.2026.115240_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.cma.2024.117581","article-title":"Operator learning with Gaussian processes","volume":"434","author":"Mora","year":"2025","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"10.1016\/j.jcp.2026.115240_bib0024","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1017\/S0962492923000089","article-title":"Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning","volume":"33","author":"De Ryck","year":"2024","journal-title":"Acta Numer."},{"issue":"2","key":"10.1016\/j.jcp.2026.115240_bib0025","doi-asserted-by":"crossref","first-page":"981","DOI":"10.1093\/imanum\/drab032","article-title":"Estimates on the generalization error of physics-informed neural networks for approximating a class of inverse problems for PDEs","volume":"42","author":"Mishra","year":"2022","journal-title":"IMA J. Numer. Anal."},{"key":"10.1016\/j.jcp.2026.115240_bib0026","unstructured":"N. Reinhardt, S. Wang, J. Zech, Statistical learning theory for neural operators, 2024. arXiv preprint arXiv: 2412.17582."},{"issue":"40","key":"10.1016\/j.jcp.2026.115240_bib0027","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.abi8605","article-title":"Learning the solution operator of parametric partial differential equations with physics-informed deeponets","volume":"7","author":"Wang","year":"2021","journal-title":"Sci. Adv."},{"issue":"3","key":"10.1016\/j.jcp.2026.115240_bib0028","first-page":"1","article-title":"Physics-informed neural operator for learning partial differential equations","volume":"1","author":"Li","year":"2024","journal-title":"ACM\/JMS J. Data Sci."},{"issue":"215","key":"10.1016\/j.jcp.2026.115240_bib0029","first-page":"1","article-title":"Learning operators with coupled attention","volume":"23","author":"Kissas","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.jcp.2026.115240_bib0030","unstructured":"J. He, X. Liu, J. Xu, MgNO: efficient parameterization of linear operators via multigrid, in: Proceedings of the Twelfth International Conference on Learning Representations (ICLR), 2024. https:\/\/arxiv.org\/abs\/2310.19809."},{"key":"10.1016\/j.jcp.2026.115240_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.physd.2024.134095","article-title":"A kernel framework for learning differential equations and their solution operators","volume":"460","author":"Long","year":"2024","journal-title":"Phys. D"},{"issue":"8023","key":"10.1016\/j.jcp.2026.115240_bib0032","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1038\/s41586-025-09005-y","article-title":"A foundation model for the earth system","volume":"641","author":"Bodnar","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.jcp.2026.115240_bib0033","series-title":"Advances in Neural Information Processing Systems","article-title":"Poseidon: efficient foundation models for PDEs","volume":"Vol. 37","author":"Herde","year":"2024"},{"key":"10.1016\/j.jcp.2026.115240_bib0034","unstructured":"Z. Ye, X. Huang, L. Chen, H. Liu, Z. Wang, B. Dong, Pdeformer: towards a foundation model for one-dimensional partial differential equations, arXiv preprint arXiv: 2402.12652(2024)."},{"key":"10.1016\/j.jcp.2026.115240_bib0035","series-title":"Advances in Neural Information Processing Systems","first-page":"120832","article-title":"Newton informed neural operator for solving nonlinear partial differential equations","volume":"Vol. 37","author":"Hao","year":"2024"},{"key":"10.1016\/j.jcp.2026.115240_bib0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.jcp.2024.113433","article-title":"Randonets: shallow networks with random projections for learning linear and nonlinear operators","volume":"520","author":"Fabiani","year":"2025","journal-title":"J. Comput. Phys."},{"issue":"4","key":"10.1016\/j.jcp.2026.115240_bib0037","doi-asserted-by":"crossref","first-page":"C1006","DOI":"10.1137\/24M1686991","article-title":"Fredholm neural networks","volume":"47","author":"Georgiou","year":"2025","journal-title":"SIAM J. Sci. Comput."},{"key":"10.1016\/j.jcp.2026.115240_bib0038","unstructured":"K. Georgiou, C. Siettos, A.N. Yannacopoulos, Fredholm neural networks for forward and inverse problems in elliptic pdes, 2025b. arXiv preprint arXiv: 2507.06038."},{"key":"10.1016\/j.jcp.2026.115240_bib0039","series-title":"Neural General Operator Networks Via Banach Fixed Point Iterations","author":"Feischl","year":"2025"},{"key":"10.1016\/j.jcp.2026.115240_bib0040","series-title":"Numerical Approximation of Partial Differential Equations","author":"Quarteroni","year":"1994"},{"key":"10.1016\/j.jcp.2026.115240_bib0041","series-title":"Nonlinear Functional Analysis and Its Applications: I: Fixed-Point Theorems","author":"Zeidler","year":"1986"},{"issue":"5","key":"10.1016\/j.jcp.2026.115240_bib0042","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1088\/0266-5611\/16\/5\/309","article-title":"On optimization techniques for solving nonlinear inverseproblems","volume":"16","author":"Haber","year":"2000","journal-title":"Inverse Probl."},{"issue":"1","key":"10.1016\/j.jcp.2026.115240_bib0043","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1088\/0266-5611\/21\/1\/019","article-title":"Quasi-newton methods for large-scale electromagnetic inverse problems","volume":"21","author":"Haber","year":"2004","journal-title":"Inverse Probl."},{"key":"10.1016\/j.jcp.2026.115240_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.compfluid.2025.106955","article-title":"Gauss-newton natural gradient descent for physics-informed computational fluid dynamics","volume":"307","author":"Jnini","year":"2026","journal-title":"Comput. Fluids"},{"issue":"2","key":"10.1016\/j.jcp.2026.115240_bib0045","doi-asserted-by":"crossref","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 Process. Mag."},{"issue":"1","key":"10.1016\/j.jcp.2026.115240_bib0046","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/JETCAS.2022.3142051","article-title":"Data-driven priors for robust psse via gauss-newton unrolled neural networks","volume":"12","author":"Yang","year":"2022","journal-title":"IEEE J. Emerg. Sel. Top. Circuits Syst."},{"issue":"3","key":"10.1016\/j.jcp.2026.115240_bib0047","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1111\/1467-9868.00294","article-title":"Bayesian calibration of computer models","volume":"63","author":"Kennedy","year":"2001","journal-title":"J. R. Stat. Soc. Ser. B (Stat. Methodol.)"},{"issue":"6","key":"10.1016\/j.jcp.2026.115240_bib0048","doi-asserted-by":"crossref","first-page":"3144","DOI":"10.1137\/20M132571X","article-title":"Sparse compression of expected solution operators","volume":"58","author":"Feischl","year":"2020","journal-title":"SIAM J. Numer. Anal."},{"issue":"2","key":"10.1016\/j.jcp.2026.115240_bib0049","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1137\/S1064827501387826","article-title":"The Wiener\u2013Askey polynomial chaos for stochastic differential equations","volume":"24","author":"Xiu","year":"2002","journal-title":"SIAM J. Sci. Comput."},{"key":"10.1016\/j.jcp.2026.115240_bib0050","series-title":"Model Order Reduction: Theory, Research Aspects and Applications","volume":"Vol. 13","author":"Schilders","year":"2008"},{"key":"10.1016\/j.jcp.2026.115240_bib0051","series-title":"Numerical Optimization","author":"Nocedal","year":"2006"},{"key":"10.1016\/j.jcp.2026.115240_bib0052","series-title":"Advances in Neural Information Processing Systems","article-title":"Attention is all you need","volume":"Vol. 30","author":"Vaswani","year":"2017"},{"issue":"300","key":"10.1016\/j.jcp.2026.115240_bib0053","first-page":"1","article-title":"Continuum attention for neural operators","volume":"26","author":"Calvello","year":"2025","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"10.1016\/j.jcp.2026.115240_bib0054","doi-asserted-by":"crossref","first-page":"A998","DOI":"10.1137\/22M154226X","article-title":"Sparse recovery of elliptic solvers from matrix-vector products","volume":"46","author":"Sch\u00e4fer","year":"2024","journal-title":"SIAM J. Sci. Comput."},{"issue":"4","key":"10.1016\/j.jcp.2026.115240_bib0055","doi-asserted-by":"crossref","DOI":"10.1145\/3658199","article-title":"Lightning-fast method of fundamental solutions","volume":"43","author":"Chen","year":"2024","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.jcp.2026.115240_bib0056","series-title":"Advances in Neural Information Processing Systems","first-page":"6007","article-title":"Openfwi: large-scale multi-structural benchmark datasets for full waveform inversion","volume":"Vol. 35","author":"Deng","year":"2022"},{"issue":"4","key":"10.1016\/j.jcp.2026.115240_bib0057","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1007\/s11222-017-9766-2","article-title":"Nested Kriging predictions for datasets with a large number of observations","volume":"28","author":"Rulli\u00e8re","year":"2018","journal-title":"Stat. Comput."},{"issue":"2","key":"10.1016\/j.jcp.2026.115240_bib0058","doi-asserted-by":"crossref","first-page":"A31","DOI":"10.1190\/geo2014-0441.1","article-title":"Frequencies of the Ricker wavelet","volume":"80","author":"Wang","year":"2015","journal-title":"Geophysics"},{"issue":"6","key":"10.1016\/j.jcp.2026.115240_bib0059","doi-asserted-by":"crossref","first-page":"WCC1","DOI":"10.1190\/1.3238367","article-title":"An overview of full-waveform inversion in exploration geophysics","volume":"74","author":"Virieux","year":"2009","journal-title":"Geophysics"},{"key":"10.1016\/j.jcp.2026.115240_bib0060","unstructured":"X. Wang, 2d 2-8 fd acoustic modeling lab, 2023, https:\/\/csim.kaust.edu.sa\/files\/SeismicInversion\/Chapter.FD\/lab.FD2.8\/lab.html. Accessed: 2025-10-07."},{"issue":"2","key":"10.1016\/j.jcp.2026.115240_bib0061","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1137\/0719025","article-title":"Inexact newton methods","volume":"19","author":"Dembo","year":"1982","journal-title":"SIAM J. Numer. Anal."},{"key":"10.1016\/j.jcp.2026.115240_bib0062","series-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","article-title":"Pytorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"10.1016\/j.jcp.2026.115240_bib0063","unstructured":"William Falcon and The PyTorch Lightning team, PyTorch lightning, 2019."},{"key":"10.1016\/j.jcp.2026.115240_bib0064","series-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","article-title":"GPyTorch: blackbox matrix-matrix Gaussian process inference with GPU acceleration","author":"Gardner","year":"2018"},{"key":"10.1016\/j.jcp.2026.115240_bib0065","series-title":"Proceedings of the First International Conference on Probabilistic Numerics","first-page":"35","article-title":"Fast Gaussian process regression for high-dimensional functions with derivative information","volume":"271","author":"Sorokin","year":"2025"},{"key":"10.1016\/j.jcp.2026.115240_bib0066","series-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"2623","article-title":"Optuna: A next-generation hyperparameter optimization framework","author":"Akiba","year":"2019"},{"issue":"1","key":"10.1016\/j.jcp.2026.115240_bib0067","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1137\/15M1013894","article-title":"Multigrid with rough coefficients and multiresolution operator decomposition from hierarchical information games","volume":"59","author":"Owhadi","year":"2017","journal-title":"Siam Rev."},{"key":"10.1016\/j.jcp.2026.115240_bib0068","series-title":"Operator-Adapted Wavelets, Fast Solvers, and Numerical Homogenization: From a Game Theoretic Approach to Numerical Approximation and Algorithm Design","volume":"Vol. 35","author":"Owhadi","year":"2019"},{"issue":"2","key":"10.1016\/j.jcp.2026.115240_bib0069","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1137\/19M129526X","article-title":"Compression, inversion, and approximate pca of dense kernel matrices at near-linear computational complexity","volume":"19","author":"Sch\u00e4fer","year":"2021","journal-title":"Multiscale Model. Simul."},{"issue":"3","key":"10.1016\/j.jcp.2026.115240_bib0070","doi-asserted-by":"crossref","first-page":"A2019","DOI":"10.1137\/20M1336254","article-title":"Sparse Cholesky factorization by Kullback\u2013Leibler minimization","volume":"43","author":"Sch\u00e4fer","year":"2021","journal-title":"SIAM J. Sci. Comput."},{"issue":"353","key":"10.1016\/j.jcp.2026.115240_bib0071","first-page":"1235","article-title":"Sparse Cholesky factorization for solving nonlinear PDEs via Gaussian processes","volume":"94","author":"Chen","year":"2025","journal-title":"Math. Comp."},{"key":"10.1016\/j.jcp.2026.115240_bib0072","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1017\/S0962492921000015","article-title":"Numerical homogenization beyond scale separation","volume":"30","author":"Altmann","year":"2021","journal-title":"Acta Numer."},{"key":"10.1016\/j.jcp.2026.115240_bib0073","unstructured":"A. Bacho, J. Lee, H. Owhadi, KROM: Kernelized reduced order modeling, 2026. arXiv preprint arXiv: 2603.00360."},{"issue":"2","key":"10.1016\/j.jcp.2026.115240_bib0074","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1137\/090771806","article-title":"Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions","volume":"53","author":"Halko","year":"2011","journal-title":"SIAM Rev."},{"issue":"5","key":"10.1016\/j.jcp.2026.115240_bib0075","doi-asserted-by":"crossref","first-page":"995","DOI":"10.1002\/cpa.22234","article-title":"Randomly pivoted Cholesky: Practical approximation of a kernel matrix with few entry evaluations","volume":"78","author":"Chen","year":"2025","journal-title":"Commun. Pure Appl. Math."},{"issue":"1-23","key":"10.1016\/j.jcp.2026.115240_bib0076","first-page":"4","article-title":"The Levenberg-Marquardt algorithm for nonlinear least squares curve-fitting problems","volume":"3","author":"Gavin","year":"2019","journal-title":"Dep. Civil Environ. Eng. Duke Univ. Aug."},{"issue":"4","key":"10.1016\/j.jcp.2026.115240_bib0077","doi-asserted-by":"crossref","first-page":"A2557","DOI":"10.1137\/22M1538971","article-title":"A Levenberg\u2013Marquardt method for nonsmooth regularized least squares","volume":"46","author":"Aravkin","year":"2024","journal-title":"SIAM J. Sci. Comput."},{"issue":"1","key":"10.1016\/j.jcp.2026.115240_bib0078","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s10589-024-00589-1","article-title":"The Levenberg\u2013Marquardt method: an overview of modern convergence theories and more","volume":"89","author":"Fischer","year":"2024","journal-title":"Comput. Optim. Appl."},{"key":"10.1016\/j.jcp.2026.115240_bib0079","unstructured":"H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozi\u00e9re, N. Goyal, E. Hambro, F. Azhar, A. Rodriguez, A. Joulin, E. Grave, G. Lample, LLaMA: open and efficient foundation language models(2023). arXiv: 2302.13971 [cs]."},{"key":"10.1016\/j.jcp.2026.115240_bib0080","series-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.jcp.2026.115240_bib0081","series-title":"Advances in Neural Information Processing Systems","first-page":"24924","article-title":"Choose a transformer: Fourier or Galerkin","volume":"Vol. 34","author":"Cao","year":"2021"},{"key":"10.1016\/j.jcp.2026.115240_bib0082","series-title":"Proceedings of the 40th International Conference on Machine Learning, ICML\u201923","article-title":"GNOT: a general neural operator transformer for operator learning","author":"Hao","year":"2023"},{"key":"10.1016\/j.jcp.2026.115240_bib0083","article-title":"Transformer for partial differential equations\u2019 operator learning","author":"Li","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.jcp.2026.115240_bib0084","series-title":"Advances in Neural Information Processing Systems","article-title":"Pretraining codomain attention neural operators for solving multiphysics pdes","volume":"Vol. 37","author":"Rahman","year":"2024"},{"issue":"2","key":"10.1016\/j.jcp.2026.115240_bib0085","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/s40687-022-00320-8","article-title":"Computational graph completion","volume":"9","author":"Owhadi","year":"2022","journal-title":"Res. Math. Sci."}],"container-title":["Journal of Computational Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0021999126005917?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0021999126005917?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T04:38:13Z","timestamp":1785386293000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0021999126005917"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":85,"alternative-id":["S0021999126005917"],"URL":"https:\/\/doi.org\/10.1016\/j.jcp.2026.115240","relation":{},"ISSN":["0021-9991"],"issn-type":[{"value":"0021-9991","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Operator learning at machine precision","name":"articletitle","label":"Article Title"},{"value":"Journal of Computational Physics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jcp.2026.115240","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115240"}}