{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T05:41:58Z","timestamp":1776836518035,"version":"3.51.2"},"reference-count":69,"publisher":"American Mathematical Society (AMS)","issue":"340","license":[{"start":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T00:00:00Z","timestamp":1700092800000},"content-version":"am","delay-in-days":365,"URL":"https:\/\/www.ams.org\/publications\/copyright-and-permissions"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Math. Comp."],"abstract":"<p>\n                    Within the framework of parameter dependent Partial Differential Equations (PDEs), we develop a constructive approach based on Deep Neural Networks for the efficient approximation of the parameter-to-solution map. The research is motivated by the limitations and drawbacks of state-of-the-art algorithms, such as the Reduced Basis method, when addressing problems that show a slow decay in the Kolmogorov\n                    <inline-formula content-type=\"math\/mathml\">\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" alttext=\"n\">\n                        <mml:semantics>\n                          <mml:mi>n<\/mml:mi>\n                          <mml:annotation encoding=\"application\/x-tex\">n<\/mml:annotation>\n                        <\/mml:semantics>\n                      <\/mml:math>\n                    <\/inline-formula>\n                    -width. Our work is based on the use of deep autoencoders, which we employ for encoding and decoding a high fidelity approximation of the solution manifold. To provide guidelines for the design of deep autoencoders, we consider a nonlinear version of the Kolmogorov\n                    <inline-formula content-type=\"math\/mathml\">\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" alttext=\"n\">\n                        <mml:semantics>\n                          <mml:mi>n<\/mml:mi>\n                          <mml:annotation encoding=\"application\/x-tex\">n<\/mml:annotation>\n                        <\/mml:semantics>\n                      <\/mml:math>\n                    <\/inline-formula>\n                    -width over which we base the concept of a minimal latent dimension. We show that the latter is intimately related to the topological properties of the solution manifold, and we provide theoretical results with particular emphasis on second order elliptic PDEs, characterizing the minimal dimension and the approximation errors of the proposed approach. The theory presented is further supported by numerical experiments, where we compare the proposed approach with classical Principal Orthogonal Decomposition (POD)-Galerkin reduced order models. In particular, we consider parametrized advection-diffusion PDEs, and we test the methodology in the presence of strong transport fields, singular terms and stochastic coefficients.\n                  <\/p>","DOI":"10.1090\/mcom\/3781","type":"journal-article","created":{"date-parts":[[2022,11,16]],"date-time":"2022-11-16T10:12:40Z","timestamp":1668593560000},"page":"483-524","source":"Crossref","is-referenced-by-count":42,"title":["A deep learning approach to Reduced Order Modelling of parameter dependent partial differential equations"],"prefix":"10.1090","volume":"92","author":[{"given":"Nicola","family":"Franco","sequence":"first","affiliation":[]},{"given":"Andrea","family":"Manzoni","sequence":"additional","affiliation":[]},{"given":"Paolo","family":"Zunino","sequence":"additional","affiliation":[]}],"member":"14","published-online":{"date-parts":[[2022,11,16]]},"reference":[{"key":"1","series-title":"Pure and Applied Mathematics, Vol. 65","volume-title":"Sobolev spaces","author":"Adams, Robert A.","year":"1975"},{"issue":"304","key":"2","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1090\/mcom\/3132","article-title":"Kolmogorov widths and low-rank approximations of parametric elliptic PDEs","volume":"86","author":"Bachmayr, Markus","year":"2017","journal-title":"Math. Comp.","ISSN":"https:\/\/id.crossref.org\/issn\/0025-5718","issn-type":"print"},{"issue":"3","key":"3","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1137\/050645142","article-title":"A stochastic collocation method for elliptic partial differential equations with random input data","volume":"45","author":"Babu\u0161ka, Ivo","year":"2007","journal-title":"SIAM J. Numer. Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/0036-1429","issn-type":"print"},{"issue":"9","key":"4","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1016\/j.crma.2004.08.006","article-title":"An \u2018empirical interpolation\u2019 method: application to efficient reduced-basis discretization of partial differential equations","volume":"339","author":"Barrault, Maxime","year":"2004","journal-title":"C. R. Math. Acad. Sci. Paris","ISSN":"https:\/\/id.crossref.org\/issn\/1631-073X","issn-type":"print"},{"key":"5","series-title":"American Mathematical Society Colloquium Publications","isbn-type":"print","doi-asserted-by":"publisher","DOI":"10.1090\/coll\/048","volume-title":"Geometric nonlinear functional analysis. Vol. 1","volume":"48","author":"Benyamini, Yoav","year":"2000","ISBN":"https:\/\/id.crossref.org\/isbn\/0821808354"},{"key":"6","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1016\/j.jcp.2016.01.040","article-title":"A nonlinear manifold-based reduced order model for multiscale analysis of heterogeneous hyperelastic materials","volume":"313","author":"Bhattacharjee, Satyaki","year":"2016","journal-title":"J. Comput. Phys.","ISSN":"https:\/\/id.crossref.org\/issn\/0021-9991","issn-type":"print"},{"key":"7","doi-asserted-by":"crossref","first-page":"121","DOI":"10.5802\/smai-jcm.74","article-title":"Model reduction and neural networks for parametric PDEs","volume":"7","author":"Bhattacharya, Kaushik","year":"2021","journal-title":"SMAI J. Comput. Math."},{"issue":"3","key":"8","doi-asserted-by":"publisher","first-page":"1457","DOI":"10.1137\/100795772","article-title":"Convergence rates for greedy algorithms in reduced basis methods","volume":"43","author":"Binev, Peter","year":"2011","journal-title":"SIAM J. Math. Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/0036-1410","issn-type":"print"},{"issue":"1","key":"9","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1137\/18M118709X","article-title":"Optimal approximation with sparsely connected deep neural networks","volume":"1","author":"B\u00f6lcskei, Helmut","year":"2019","journal-title":"SIAM J. Math. Data Sci."},{"key":"10","doi-asserted-by":"crossref","unstructured":"K. Borsuk, Drei S\u00e4tze \u00fcber die n-dimensionale euklidische Sph\u00e4re, Fund. Math. 20 (1933), 177\u2013190.","DOI":"10.4064\/fm-20-1-177-190"},{"key":"11","doi-asserted-by":"crossref","unstructured":"T. Bui-Thanh, C. Burstedde, O. Ghattas, J. Martin, G. Stadler, and L. Wilcox, Extreme-scale UQ for Bayesian inverse problems governed by PDEs, International Conference for High Performance Computing, Networking, Storage and Analysis, SC. 1-11. 10.1109\/SC.2012.56 (2012).","DOI":"10.1109\/SC.2012.56"},{"issue":"4","key":"12","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/BF01389461","article-title":"\ud835\udc3f\u00b2 estimates for the finite element method for the Dirichlet problem with singular data","volume":"47","author":"Casas, Eduardo","year":"1985","journal-title":"Numer. Math.","ISSN":"https:\/\/id.crossref.org\/issn\/0029-599X","issn-type":"print"},{"key":"13","unstructured":"T. Q. Chen, Y. Rubanova, J. Bettencourt, and D. Duvenaud, Neural ordinary differential equations, Adv. Neural Inform. Process. Syst. 31 (2018)."},{"key":"14","doi-asserted-by":"publisher","first-page":"Paper No. 110666, 28","DOI":"10.1016\/j.jcp.2021.110666","article-title":"Physics-informed machine learning for reduced-order modeling of nonlinear problems","volume":"446","author":"Chen, Wenqian","year":"2021","journal-title":"J. Comput. Phys.","ISSN":"https:\/\/id.crossref.org\/issn\/0021-9991","issn-type":"print"},{"key":"15","first-page":"368","article-title":"Principio di massimo forte per sottosoluzioni di equazioni ellittiche di tipo variazionale","volume":"22","author":"Chicco, Maurizio","year":"1967","journal-title":"Boll. Un. Mat. Ital. (3)"},{"issue":"3","key":"16","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1007\/s10208-021-09494-z","article-title":"Optimal stable nonlinear approximation","volume":"22","author":"Cohen, Albert","year":"2022","journal-title":"Found. Comput. Math.","ISSN":"https:\/\/id.crossref.org\/issn\/1615-3375","issn-type":"print"},{"issue":"1","key":"17","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/s00365-021-09548-z","article-title":"Nonlinear approximation and (deep) ReLU networks","volume":"55","author":"Daubechies, I.","year":"2022","journal-title":"Constr. Approx.","ISSN":"https:\/\/id.crossref.org\/issn\/0176-4276","issn-type":"print"},{"issue":"4","key":"18","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1007\/BF01171759","article-title":"Optimal nonlinear approximation","volume":"63","author":"DeVore, Ronald A.","year":"1989","journal-title":"Manuscripta Math.","ISSN":"https:\/\/id.crossref.org\/issn\/0025-2611","issn-type":"print"},{"key":"19","series-title":"American Mathematical Society Colloquium Publications","isbn-type":"print","doi-asserted-by":"publisher","DOI":"10.1090\/coll\/063","volume-title":"Geometric group theory","volume":"63","author":"Dru\u0163u, Cornelia","year":"2018","ISBN":"https:\/\/id.crossref.org\/isbn\/9781470411046"},{"key":"20","doi-asserted-by":"crossref","first-page":"353","DOI":"10.2140\/pjm.1951.1.353","article-title":"An extension of Tietze\u2019s theorem","volume":"1","author":"Dugundji, J.","year":"1951","journal-title":"Pacific J. Math.","ISSN":"https:\/\/id.crossref.org\/issn\/0030-8730","issn-type":"print"},{"key":"21","series-title":"North-Holland Mathematical Library","isbn-type":"print","volume-title":"Dimension theory","volume":"19","author":"Engelking, Ryszard","year":"1978","ISBN":"https:\/\/id.crossref.org\/isbn\/0444851763"},{"key":"22","series-title":"Graduate Studies in Mathematics","isbn-type":"print","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/019","volume-title":"Partial differential equations","volume":"19","author":"Evans, Lawrence C.","year":"2010","ISBN":"https:\/\/id.crossref.org\/isbn\/9780821849743","edition":"2"},{"issue":"3","key":"23","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1007\/BF01391412","article-title":"Solution manifolds and submanifolds of parametrized equations and their discretization errors","volume":"45","author":"Fink, James P.","year":"1984","journal-title":"Numer. Math.","ISSN":"https:\/\/id.crossref.org\/issn\/0029-599X","issn-type":"print"},{"issue":"2","key":"24","doi-asserted-by":"publisher","first-page":"Paper No. 61, 36","DOI":"10.1007\/s10915-021-01462-7","article-title":"A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs","volume":"87","author":"Fresca, Stefania","year":"2021","journal-title":"J. Sci. Comput.","ISSN":"https:\/\/id.crossref.org\/issn\/0885-7474","issn-type":"print"},{"key":"25","doi-asserted-by":"publisher","first-page":"Paper No. 114181, 27","DOI":"10.1016\/j.cma.2021.114181","article-title":"POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition","volume":"388","author":"Fresca, Stefania","year":"2022","journal-title":"Comput. Methods Appl. Mech. Engrg.","ISSN":"https:\/\/id.crossref.org\/issn\/0045-7825","issn-type":"print"},{"issue":"1","key":"26","doi-asserted-by":"publisher","first-page":"Paper No. 22, 37","DOI":"10.1007\/s10915-021-01532-w","article-title":"Numerical solution of the parametric diffusion equation by deep neural networks","volume":"88","author":"Geist, Moritz","year":"2021","journal-title":"J. Sci. Comput.","ISSN":"https:\/\/id.crossref.org\/issn\/0885-7474","issn-type":"print"},{"key":"27","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/j.aml.2019.05.013","article-title":"Decay of the Kolmogorov \ud835\udc41-width for wave problems","volume":"96","author":"Greif, Constantin","year":"2019","journal-title":"Appl. Math. Lett.","ISSN":"https:\/\/id.crossref.org\/issn\/0893-9659","issn-type":"print"},{"key":"28","doi-asserted-by":"crossref","unstructured":"J. Gu, Z. Wang, J. Kuen, L. Ma, A. Shahroudy, B. Shuai, T. Liu, X. Wang, G. Wang, J. Cai, and T. Chen, Recent advances in convolutional neural networks, Pattern Recognit. 77 (2018), 354-377.","DOI":"10.1016\/j.patcog.2017.10.013"},{"issue":"5","key":"29","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1142\/S0219530519410021","article-title":"Error bounds for approximations with deep ReLU neural networks in \ud835\udc4a^{\ud835\udc60,\ud835\udc5d} norms","volume":"18","author":"G\u00fchring, Ingo","year":"2020","journal-title":"Anal. Appl. (Singap.)","ISSN":"https:\/\/id.crossref.org\/issn\/0219-5305","issn-type":"print"},{"key":"30","doi-asserted-by":"crossref","unstructured":"I. G\u00fchring and M. Raslan, Approximation rates for neural networks with encodable weights in smoothness spaces, Neural Netw. 134 (2021), 107-130.","DOI":"10.1016\/j.neunet.2020.11.010"},{"key":"31","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1016\/j.cma.2018.07.017","article-title":"Reduced order modeling for nonlinear structural analysis using Gaussian process regression","volume":"341","author":"Guo, Mengwu","year":"2018","journal-title":"Comput. Methods Appl. Mech. Engrg.","ISSN":"https:\/\/id.crossref.org\/issn\/0045-7825","issn-type":"print"},{"key":"32","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun, Delving deep into rectifiers: surpassing human-level performance on imagenet classification, Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015, pp. 1026\u20131034.","DOI":"10.1109\/ICCV.2015.123"},{"issue":"5786","key":"33","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"Hinton, G. E.","year":"2006","journal-title":"Science","ISSN":"https:\/\/id.crossref.org\/issn\/0036-8075","issn-type":"print"},{"key":"34","volume-title":"Topology","author":"Hocking, John G.","year":"1961"},{"issue":"7","key":"35","doi-asserted-by":"publisher","first-page":"Paper No. 075005, 49","DOI":"10.1088\/1361-6420\/ac6d02","article-title":"Parameter identification for elliptic boundary value problems: an abstract framework and applications","volume":"38","author":"Hoffmann, Heiko","year":"2022","journal-title":"Inverse Problems","ISSN":"https:\/\/id.crossref.org\/issn\/0266-5611","issn-type":"print"},{"issue":"1","key":"36","doi-asserted-by":"publisher","first-page":"1398","DOI":"10.1137\/16M1055736","article-title":"A goal-oriented reduced basis methods-accelerated generalized polynomial chaos algorithm","volume":"4","author":"Jiang, Jiahua","year":"2016","journal-title":"SIAM\/ASA J. Uncertain. Quantif."},{"key":"37","unstructured":"D. P. Kingma and J. Ba, Adam: a method for stochastic optimization, Conference Paper at the 3rd International Conference for Learning Representations, San Diego, 2015."},{"issue":"2","key":"38","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1137\/090759239","article-title":"A certified reduced basis method for the Fokker-Planck equation of dilute polymeric fluids: FENE dumbbells in extensional flow","volume":"32","author":"Knezevic, David J.","year":"2010","journal-title":"SIAM J. Sci. Comput.","ISSN":"https:\/\/id.crossref.org\/issn\/1064-8275","issn-type":"print"},{"issue":"1","key":"39","doi-asserted-by":"publisher","first-page":"107","DOI":"10.2307\/1968691","article-title":"\u00dcber die beste Ann\u00e4herung von Funktionen einer gegebenen Funktionenklasse","volume":"37","author":"Kolmogoroff, A.","year":"1936","journal-title":"Ann. of Math. (2)","ISSN":"https:\/\/id.crossref.org\/issn\/0003-486X","issn-type":"print"},{"issue":"1","key":"40","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/s00365-021-09551-4","article-title":"A theoretical analysis of deep neural networks and parametric PDEs","volume":"55","author":"Kutyniok, Gitta","year":"2022","journal-title":"Constr. Approx.","ISSN":"https:\/\/id.crossref.org\/issn\/0176-4276","issn-type":"print"},{"issue":"1","key":"41","doi-asserted-by":"publisher","first-page":"Paper No. 11, 32","DOI":"10.1007\/s10444-020-09834-7","article-title":"Efficient approximation of solutions of parametric linear transport equations by ReLU DNNs","volume":"47","author":"Laakmann, Fabian","year":"2021","journal-title":"Adv. Comput. Math.","ISSN":"https:\/\/id.crossref.org\/issn\/1019-7168","issn-type":"print"},{"issue":"1","key":"42","doi-asserted-by":"publisher","first-page":"tnac001, 141","DOI":"10.1093\/imatrm\/tnac001","article-title":"Error estimates for DeepONets: a deep learning framework in infinite dimensions","volume":"6","author":"Lanthaler, Samuel","year":"2022","journal-title":"Trans. Math. Appl."},{"issue":"1","key":"43","first-page":"113","article-title":"Generalized reduced basis methods and \ud835\udc5b-width estimates for the approximation of the solution manifold of parametric PDEs","volume":"6","author":"Lassila, Toni","year":"2013","journal-title":"Boll. Unione Mat. Ital. (9)","ISSN":"https:\/\/id.crossref.org\/issn\/1972-6724","issn-type":"print"},{"key":"44","doi-asserted-by":"publisher","first-page":"108973","DOI":"10.1016\/j.jcp.2019.108973","article-title":"Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders","volume":"404","author":"Lee, Kookjin","year":"2020","journal-title":"J. Comput. Phys.","ISSN":"https:\/\/id.crossref.org\/issn\/0021-9991","issn-type":"print"},{"key":"45","unstructured":"I. Loshchilov and F. Hutter, Decoupled weight decay regularization, Conference Paper at ICLR 2019, 2019."},{"key":"46","doi-asserted-by":"crossref","unstructured":"L. Lu, P. Jin, and G. E. Karniadakis, Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators, Nat. Mach. Intelligence 3 (2021), no. 3, 218-229.","DOI":"10.1038\/s42256-021-00302-5"},{"key":"47","series-title":"Mathematics in Science and Engineering","isbn-type":"print","volume-title":"Proper orthogonal decomposition methods for partial differential equations","author":"Luo, Zhendong","year":"2019","ISBN":"https:\/\/id.crossref.org\/isbn\/9780128167984"},{"issue":"2","key":"48","doi-asserted-by":"publisher","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, Siddhartha","year":"2022","journal-title":"IMA J. Numer. Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/0272-4979","issn-type":"print"},{"issue":"3","key":"49","doi-asserted-by":"publisher","first-page":"1811","DOI":"10.1137\/20M1344883","article-title":"Enhancing accuracy of deep learning algorithms by training with low-discrepancy sequences","volume":"59","author":"Mishra, Siddhartha","year":"2021","journal-title":"SIAM J. Numer. Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/0036-1429","issn-type":"print"},{"key":"50","doi-asserted-by":"crossref","unstructured":"N. T. M\u00fccke, S. M. Boht\u00e9, and C. W. Oosterlee, Reduced order modeling for parameterized time-dependent PDEs using spatially and memory aware deep learning, J. Comput. Sci. 101408 (2021).","DOI":"10.1016\/j.jocs.2021.101408"},{"key":"51","volume-title":"Les m\\'{e}thodes directes en th\\'{e}orie des \\'{e}quations elliptiques","author":"Ne\u010das, Jind\u0159ich","year":"1967"},{"key":"52","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1016\/j.jcp.2015.09.046","article-title":"Efficient model reduction of parametrized systems by matrix discrete empirical interpolation","volume":"303","author":"Negri, Federico","year":"2015","journal-title":"J. Comput. Phys.","ISSN":"https:\/\/id.crossref.org\/issn\/0021-9991","issn-type":"print"},{"key":"53","unstructured":"M. Ohlberger and S. Rave, Reduced basis methods: success, limitations and future challenges, Proceedings of the Conference Algoritmy, 2016, pp. 1\u201312."},{"key":"54","unstructured":"S. Park, C. Yun, J. Lee, and J. Shin, Minimum width for universal approximation, International Conference on Learning Representations, 2021."},{"key":"55","doi-asserted-by":"crossref","unstructured":"P. Petersen and F. Voigtlaender, Optimal approximation of piecewise smooth functions using deep ReLU neural networks, Neural Netw. 108 (2018), 296-330.","DOI":"10.1016\/j.neunet.2018.08.019"},{"key":"56","isbn-type":"print","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1017\/S0962492900002919","article-title":"Approximation theory of the MLP model in neural networks","author":"Pinkus, Allan","year":"1999","ISBN":"https:\/\/id.crossref.org\/isbn\/0521770882"},{"key":"57","series-title":"Unitext","isbn-type":"print","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-15431-2","volume-title":"Reduced basis methods for partial differential equations","volume":"92","author":"Quarteroni, Alfio","year":"2016","ISBN":"https:\/\/id.crossref.org\/isbn\/9783319154305"},{"key":"58","series-title":"Springer Series in Computational Mathematics","isbn-type":"print","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-85268-1","volume-title":"Numerical approximation of partial differential equations","volume":"23","author":"Quarteroni, Alfio","year":"1994","ISBN":"https:\/\/id.crossref.org\/isbn\/3540571116"},{"key":"59","doi-asserted-by":"crossref","unstructured":"F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner, and G. Monfardini, The graph neural network model, IEEE Trans. Neural Netw. 20 (2008), no. 1, 61\u201380.","DOI":"10.1109\/TNN.2008.2005605"},{"issue":"1","key":"60","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1142\/S0219530518500203","article-title":"Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ","volume":"17","author":"Schwab, Christoph","year":"2019","journal-title":"Anal. Appl. (Singap.)","ISSN":"https:\/\/id.crossref.org\/issn\/0219-5305","issn-type":"print"},{"key":"61","doi-asserted-by":"crossref","unstructured":"J. Schmidhuber, Deep learning in neural networks: an overview, Neural Netw. 61 (2015), 85-117.","DOI":"10.1016\/j.neunet.2014.09.003"},{"issue":"2200","key":"62","doi-asserted-by":"publisher","first-page":"20160809","DOI":"10.1098\/rspa.2016.0809","article-title":"Reduced-order modelling of parameter-dependent, linear and nonlinear dynamic partial differential equation models","volume":"473","author":"Shah, A. A.","year":"2017","journal-title":"Proc. A","ISSN":"https:\/\/id.crossref.org\/issn\/1364-5021","issn-type":"print"},{"key":"63","doi-asserted-by":"crossref","unstructured":"Y. Shin, J. Darbon, and G. E. Karniadakis, On the convergence and generalization of physics informed neural networks, Communications in Computational Physics 28 (2020), no. 5, 2042-2074.","DOI":"10.4208\/cicp.OA-2020-0193"},{"key":"64","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.acha.2021.12.005","article-title":"High-order approximation rates for shallow neural networks with cosine and \ud835\udc45\ud835\udc52\ud835\udc3f\ud835\udc48^{\ud835\udc58} activation functions","volume":"58","author":"Siegel, Jonathan W.","year":"2022","journal-title":"Appl. Comput. Harmon. Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/1063-5203","issn-type":"print"},{"key":"65","isbn-type":"print","first-page":"248","article-title":"Embedding and knotting of manifolds in Euclidean spaces","author":"Skopenkov, Arkadiy B.","year":"2008","ISBN":"https:\/\/id.crossref.org\/isbn\/9780521705646"},{"key":"66","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/j.jcp.2019.01.031","article-title":"Non-intrusive reduced order modeling of unsteady flows using artificial neural networks with application to a combustion problem","volume":"384","author":"Wang, Qian","year":"2019","journal-title":"J. Comput. Phys.","ISSN":"https:\/\/id.crossref.org\/issn\/0021-9991","issn-type":"print"},{"key":"67","doi-asserted-by":"crossref","unstructured":"D. Yarotski, Error bounds for approximations with deep ReLU networks, Neural Netw. 94, 103-114.","DOI":"10.1016\/j.neunet.2017.07.002"},{"key":"68","unstructured":"H. Zhang, X. Gao, J. Unterman, and T. Arodz, Approximation capabilities of neural ODEs and invertible residual networks, International Conference on Machine Learning, PMLR, 2020, pp. 11086-11095."},{"key":"69","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/j.jcp.2018.04.018","article-title":"Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification","volume":"366","author":"Zhu, Yinhao","year":"2018","journal-title":"J. Comput. Phys.","ISSN":"https:\/\/id.crossref.org\/issn\/0021-9991","issn-type":"print"}],"container-title":["Mathematics of Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ams.org\/mcom\/2023-92-340\/S0025-5718-2022-03781-9\/S0025-5718-2022-03781-9.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T04:48:24Z","timestamp":1776833304000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ams.org\/mcom\/2023-92-340\/S0025-5718-2022-03781-9\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,16]]},"references-count":69,"journal-issue":{"issue":"340","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["S0025-5718-2022-03781-9"],"URL":"https:\/\/doi.org\/10.1090\/mcom\/3781","archive":["CLOCKSS","Portico"],"relation":{},"ISSN":["1088-6842","0025-5718"],"issn-type":[{"value":"1088-6842","type":"electronic"},{"value":"0025-5718","type":"print"}],"subject":[],"published":{"date-parts":[[2022,11,16]]}}}