{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T06:13:48Z","timestamp":1772777628763,"version":"3.50.1"},"reference-count":77,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,6,5]],"date-time":"2021-06-05T00:00:00Z","timestamp":1622851200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,6,5]],"date-time":"2021-06-05T00:00:00Z","timestamp":1622851200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003065","name":"University of Vienna","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003065","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sci Comput"],"published-print":{"date-parts":[[2021,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We perform a comprehensive numerical study of the effect of approximation-theoretical results for neural networks on practical learning problems in the context of numerical analysis. As the underlying model, we study the machine-learning-based solution of parametric partial differential equations. Here, approximation theory for fully-connected neural networks predicts that the performance of the model should depend only very mildly on the dimension of the parameter space and is determined by the intrinsic dimension of the solution manifold of the parametric partial differential equation. We use various methods to establish comparability between test-cases by minimizing the effect of the choice of test-cases on the optimization and sampling aspects of the learning problem. We find strong support for the hypothesis that approximation-theoretical effects heavily influence the practical behavior of learning problems in numerical analysis. Turning to practically more successful and modern architectures, at the end of this study we derive improved error bounds by focusing on convolutional neural networks.<\/jats:p>","DOI":"10.1007\/s10915-021-01532-w","type":"journal-article","created":{"date-parts":[[2021,6,5]],"date-time":"2021-06-05T12:03:06Z","timestamp":1622894586000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":51,"title":["Numerical Solution of the Parametric Diffusion Equation by Deep Neural Networks"],"prefix":"10.1007","volume":"88","author":[{"given":"Moritz","family":"Geist","sequence":"first","affiliation":[]},{"given":"Philipp","family":"Petersen","sequence":"additional","affiliation":[]},{"given":"Mones","family":"Raslan","sequence":"additional","affiliation":[]},{"given":"Reinhold","family":"Schneider","sequence":"additional","affiliation":[]},{"given":"Gitta","family":"Kutyniok","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,6,5]]},"reference":[{"key":"1532_CR1","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Man\u00e9, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Vi\u00e9gas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., Zheng, X.: TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems (2015). Software available from tensorflow.org"},{"key":"1532_CR2","unstructured":"Adcock, B., Brugiapaglia, S., Dexter, N., Moraga, S.: Deep neural networks are effective at learning high-dimensional Hilbert-valued functions from limited data. arXiv preprint arXiv:2012.06081 (2020)"},{"key":"1532_CR3","unstructured":"Adcock, B., Dexter, N.: The gap between theory and practice in function approximation with deep neural networks. arXiv preprint arXiv:2001.07523 (2020)"},{"key":"1532_CR4","unstructured":"Aln\u00e6s, M.S., Blechta, J., Hake, J., Johansson, A., Kehlet, B., Logg, A., Richardson, C., Ring, J., Rognes, M.E., Wells, G.N.: The FEniCS Project Version 1.5. Arch. Numer. Softw. 3(100) (2015)"},{"issue":"304","key":"1532_CR5","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1090\/mcom\/3132","volume":"86","author":"M Bachmayr","year":"2017","unstructured":"Bachmayr, M., Cohen, A.: Kolmogorov widths and low-rank approximations of parametric elliptic PDEs. Math. Comput. 86(304), 701\u2013724 (2017)","journal-title":"Math. Comput."},{"issue":"4","key":"1532_CR6","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1093\/imanum\/drx052","volume":"38","author":"M Bachmayr","year":"2018","unstructured":"Bachmayr, M., Cohen, A., Dahmen, W.: Parametric PDEs: sparse or low-rank approximations? IMA J. Numer. Anal. 38(4), 1661\u20131708 (2018)","journal-title":"IMA J. Numer. Anal."},{"issue":"3","key":"1532_CR7","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1109\/18.256500","volume":"39","author":"A Barron","year":"1993","unstructured":"Barron, A.: Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inf. Theory 39(3), 930\u2013945 (1993)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"1532_CR8","unstructured":"Beck, C., Becker, S., Grohs, P., Jaafari, N., Jentzen, A.: Solving stochastic differential equations and Kolmogorov equations by means of deep learning. arXiv preprint arXiv:1806.00421 (2018)"},{"key":"1532_CR9","doi-asserted-by":"publisher","first-page":"1563","DOI":"10.1007\/s00332-018-9525-3","volume":"29","author":"C Beck","year":"2019","unstructured":"Beck, C., Weinan, E., Jentzen, A.: Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations. J. Nonlinear Sci. 29, 1563\u20131619 (2019)","journal-title":"J. Nonlinear Sci."},{"issue":"8","key":"1532_CR10","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1073\/pnas.38.8.716","volume":"38","author":"R Bellman","year":"1952","unstructured":"Bellman, R.: On the theory of dynamic programming. Proc. Natl. Acad. Sci. U.S.A. 38(8), 716 (1952)","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"1532_CR11","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1016\/j.jcp.2019.01.036","volume":"384","author":"J Berg","year":"2019","unstructured":"Berg, J., Nystr\u00f6m, K.: Data-driven discovery of PDEs in complex datasets. J. Comput. Phys. 384, 239\u2013252 (2019)","journal-title":"J. Comput. Phys."},{"key":"1532_CR12","unstructured":"Berner, J., Grohs, P., Jentzen, A.: Analysis of the generalization error: empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations. arXiv preprint arXiv:1809.03062 (2018)"},{"key":"1532_CR13","unstructured":"Bhattacharya, K., Hosseini, B., Kovachki, N.B., Stuart, A.M.: Model reduction and neural networks for parametric PDEs. arXiv preprintarXiv:2005.03180 (2020)"},{"key":"1532_CR14","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1137\/18M118709X","volume":"1","author":"H B\u00f6lcskei","year":"2019","unstructured":"B\u00f6lcskei, H., Grohs, P., Kutyniok, G., Petersen, P.C.: Optimal approximation with sparsely connected deep neural networks. SIAM J. Math. Data Sci. 1, 8\u201345 (2019)","journal-title":"SIAM J. Math. Data Sci."},{"key":"1532_CR15","unstructured":"Brevis, I., Muga, I., van\u00a0der Zee, K.G.: Data-driven finite elements methods: machine learning acceleration of goal-oriented computations. arXiv preprint arXiv:2003.04485 (2020)"},{"key":"1532_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S0962492915000033","volume":"24","author":"A Cohen","year":"2015","unstructured":"Cohen, A., DeVore, R.: Approximation of high-dimensional parametric PDEs. Acta Numer. 24, 1\u2013159 (2015)","journal-title":"Acta Numer."},{"key":"1532_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1090\/S0273-0979-01-00923-5","volume":"39","author":"F Cucker","year":"2002","unstructured":"Cucker, F., Smale, S.: On the mathematical foundations of learning. Bull. Am. Math. Soc. 39, 1\u201349 (2002)","journal-title":"Bull. Am. Math. Soc."},{"key":"1532_CR18","doi-asserted-by":"crossref","unstructured":"Cucker, F., Zhou, D.-X.: Learning Theory: An Approximation Theory Viewpoint, Cambridge Monographs on Applied and Computational Mathematics. Cambridge University Press (2007)","DOI":"10.1017\/CBO9780511618796"},{"key":"1532_CR19","doi-asserted-by":"crossref","unstructured":"Dal\u00a0Santo, N., Deparis, S., Pegolotti, L.: Data driven approximation of parametrized PDEs by Reduced Basis and Neural Networks. arXiv preprint arXiv:1904.01514 (2019)","DOI":"10.1016\/j.jcp.2020.109550"},{"key":"1532_CR20","doi-asserted-by":"publisher","first-page":"2503","DOI":"10.1007\/s10444-019-09723-8","volume":"45","author":"M Eigel","year":"2019","unstructured":"Eigel, M., Schneider, R., Trunschke, P., Wolf, S.: Variational Monte Carlo-bridging concepts of machine learning and high dimensional partial differential equations. Adv. Comput. Math. 45, 2503\u20132532 (2019)","journal-title":"Adv. Comput. Math."},{"key":"1532_CR21","unstructured":"Elbr\u00e4chter, D., Grohs, P., Jentzen, A., Schwab, C.: DNN expression rate analysis of high-dimensional PDEs: application to option pricing. arXiv preprint arXiv:1809.07669 (2018)"},{"issue":"11","key":"1532_CR22","doi-asserted-by":"publisher","first-page":"5255","DOI":"10.1021\/acs.jctc.7b00577","volume":"13","author":"FA Faber","year":"2017","unstructured":"Faber, F.A., Hutchison, L., Huang, B., Gilmer, J., Schoenholz, S.S., Dahl, G.E., Vinyals, O., Kearnes, S., Riley, P.F., von Lilienfeld, O.A.: Prediction errors of molecular machine learning models lower than hybrid DFT error. J. Chem. Theory Comput. 13(11), 5255\u20135264 (2017)","journal-title":"J. Chem. Theory Comput."},{"key":"1532_CR23","unstructured":"Fokina, D., Oseledets, I.: Growing axons: Greedy learning of neural networks with application to function approximation. arXiv preprint arXiv:1910.12686 (2019)"},{"key":"1532_CR24","unstructured":"Grohs, P., Hornung, F., Jentzen, A., von Wurstemberger, P.: A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black\u2013Scholes partial differential equations. arXiv preprint arXiv:1809.02362 (2018)"},{"key":"1532_CR25","unstructured":"Han, J., Jentzen, A., Weinan, E.: Overcoming the curse of dimensionality: solving high-dimensional partial differential equations using deep learning. arXiv preprint arXiv:1707.02568 (2017)"},{"issue":"34","key":"1532_CR26","doi-asserted-by":"publisher","first-page":"8505","DOI":"10.1073\/pnas.1718942115","volume":"115","author":"J Han","year":"2018","unstructured":"Han, J., Jentzen, A., Weinan, E.: Solving high-dimensional partial differential equations using deep learning. Proc. Natl. Acad. Sci. USA 115(34), 8505\u20138510 (2018)","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"1532_CR27","doi-asserted-by":"crossref","unstructured":"Han, J., Nica, M., Stinchcombe, A.R.: A derivative-free method for solving elliptic partial differential equations with deep neural networks. arXiv preprint arXiv:2001.06145 (2020)","DOI":"10.1016\/j.jcp.2020.109672"},{"issue":"10","key":"1532_CR28","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1038\/s41557-020-0544-y","volume":"12","author":"J Hermann","year":"2020","unstructured":"Hermann, J., Sch\u00e4tzle, Z., No\u00e9, F.: Deep-neural-network solution of the electronic Schr\u00f6dinger equation. Nat. Chem. 12(10), 891\u2013897 (2020)","journal-title":"Nat. Chem."},{"key":"1532_CR29","doi-asserted-by":"crossref","unstructured":"Herrmann, L., Schwab, C., Zech, J.: Deep ReLU Neural Network Expression Rates for Data-to-QoI Maps in Bayesian PDE Inversion. Technical Report 2020-02, Seminar for Applied Mathematics, ETH Z\u00fcrich (2020)","DOI":"10.1088\/1361-6420\/abaf64"},{"key":"1532_CR30","volume-title":"Certified Reduced Basis Methods for Parametrized Partial Differential Equations, Springer Briefs in Mathematics","author":"J Hesthaven","year":"2015","unstructured":"Hesthaven, J., Rozza, G., Stamm, B.: Certified Reduced Basis Methods for Parametrized Partial Differential Equations, Springer Briefs in Mathematics, 1st edn. Springer, Zurich (2015)","edition":"1"},{"key":"1532_CR31","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.jcp.2018.02.037","volume":"363","author":"JS Hesthaven","year":"2018","unstructured":"Hesthaven, J.S., Ubbiali, S.: Non-intrusive reduced order modeling of nonlinear problems using neural networks. J. Comput. Phys. 363, 55\u201378 (2018)","journal-title":"J. Comput. Phys."},{"issue":"1","key":"1532_CR32","doi-asserted-by":"publisher","first-page":"1350001","DOI":"10.1142\/S0219530513500012","volume":"11","author":"VH Hoang","year":"2013","unstructured":"Hoang, V.H., Schwab, C.: Analytic regularity and polynomial approximation of stochastic, parametric elliptic multiscale PDEs. Anal. Appl. (Singap.) 11(1), 1350001 (2013)","journal-title":"Anal. Appl. (Singap.)"},{"key":"1532_CR33","doi-asserted-by":"crossref","unstructured":"Hutzenthaler, M., Jentzen, A., Kruse, T., Nguyen, T.: A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations. arXiv preprint arXiv:1901.10854 (2019)","DOI":"10.1007\/s42985-019-0006-9"},{"key":"1532_CR34","unstructured":"Jentzen, A., Salimova, D., Welti, T.: A proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of Kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficients. arXiv preprintarXiv:1809.07321 (2018)"},{"key":"1532_CR35","unstructured":"Khoo, Y., Lu, J., Ying, L.: Solving parametric PDE problems with artificial neural networks. arXiv preprint arXiv:1707.03351 (2017)"},{"key":"1532_CR36","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"1532_CR37","doi-asserted-by":"crossref","unstructured":"Kutyniok, G., Petersen, P.C., Raslan, M., Schneider, R.: A Theoretical analysis of deep neural networks and parametric PDEs. In: Constructive Approximation (2020)","DOI":"10.1007\/s00365-021-09551-4"},{"issue":"5","key":"1532_CR38","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1109\/72.712178","volume":"9","author":"IE Lagaris","year":"1998","unstructured":"Lagaris, I.E., Likas, A., Fotiadis, D.I.: Artificial neural networks for solving ordinary and partial differential equations. IEEE Trans. Neural Netw. 9(5), 987\u20131000 (1998)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"11","key":"1532_CR39","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"1532_CR40","doi-asserted-by":"publisher","first-page":"108973","DOI":"10.1016\/j.jcp.2019.108973","volume":"404","author":"K Lee","year":"2020","unstructured":"Lee, K., Carlberg, K.T.: Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders. J. Comput. Phys. 404, 108973 (2020)","journal-title":"J. Comput. Phys."},{"key":"1532_CR41","unstructured":"Lu, J., Shen, Z., Yang, H., Zhang, S.: Deep network approximation for smooth functions. arXiv preprint arXiv:2001.03040 (2020)"},{"key":"1532_CR42","unstructured":"Lu, L., Meng, X., Mao, Z., Karniadakis, G.: DeepXDE: a deep learning library for solving differential equations. arXiv preprint arXiv:1907.04502 (2019)"},{"issue":"24","key":"1532_CR43","doi-asserted-by":"publisher","first-page":"241715","DOI":"10.1063\/1.5011181","volume":"148","author":"N Lubbers","year":"2018","unstructured":"Lubbers, N., Smith, J.S., Barros, K.: Hierarchical modeling of molecular energies using a deep neural network. J. Chem. Phys. 148(24), 241715 (2018)","journal-title":"J. Chem. Phys."},{"key":"1532_CR44","unstructured":"Lye, K., Mishra, S., Molinaro, R.: A Multi-level procedure for enhancing accuracy of machine learning algorithms. Technical Report 2019-54, Seminar for Applied Mathematics, ETH Z\u00fcrich, Switzerland (2019)"},{"key":"1532_CR45","unstructured":"Marcati, C., Opschoor, J.A., Petersen, P.C., Schwab, C.: Exponential relu neural network approximation rates for point and edge singularities. arXiv preprint arXiv:2010.12217 (2020)"},{"issue":"1","key":"1532_CR46","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1162\/neco.1996.8.1.164","volume":"8","author":"H Mhaskar","year":"1996","unstructured":"Mhaskar, H.: Neural networks for optimal approximation of smooth and analytic functions. Neural Comput. 8(1), 164\u2013177 (1996)","journal-title":"Neural Comput."},{"key":"1532_CR47","doi-asserted-by":"crossref","unstructured":"Nelsen, N., Stuart, A.: The random feature model for input\u2013output maps between Banach spaces. arXiv preprint arXiv:2005.10224 (2020)","DOI":"10.1137\/20M133957X"},{"issue":"4","key":"1532_CR48","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1016\/j.jco.2008.11.002","volume":"25","author":"E Novak","year":"2009","unstructured":"Novak, E., Wo\u017aniakowski, H.: Approximation of infinitely differentiable multivariate functions is intractable. J. Complex. 25(4), 398\u2013404 (2009)","journal-title":"J. Complex."},{"key":"1532_CR49","unstructured":"Ohlberger, M., Rave, S.: Reduced basis methods: success, limitations and future challenges. arXiv preprint arXiv:1511.02021v2 (2016)"},{"issue":"5","key":"1532_CR50","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1142\/S0219530519410136","volume":"18","author":"J Opschoor","year":"2020","unstructured":"Opschoor, J., Petersen, P.C., Schwab, C.: Deep ReLU networks and high-order finite element methods. Anal. Appl. 18(5), 715\u2013770 (2020)","journal-title":"Anal. Appl."},{"key":"1532_CR51","doi-asserted-by":"crossref","unstructured":"Petersen, P., Laakmann, F.: Efficient approximation of solutions of parametric linear transport equations by ReLU DNNs. In: Advances in Computational Mathematics, vol. 47 (2021)","DOI":"10.1007\/s10444-020-09834-7"},{"key":"1532_CR52","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.neunet.2018.08.019","volume":"180","author":"PC Petersen","year":"2018","unstructured":"Petersen, P.C., Voigtlaender, F.: Optimal approximation of piecewise smooth functions using deep ReLU neural networks. Neural Netw. 180, 296\u2013330 (2018)","journal-title":"Neural Netw."},{"key":"1532_CR53","doi-asserted-by":"publisher","first-page":"1567","DOI":"10.1090\/proc\/14789","volume":"148","author":"PC Petersen","year":"2020","unstructured":"Petersen, P.C., Voigtlaender, F.: Equivalence of approximation by convolutional neural networks and fully-connected networks. Proc. Am. Math. Soc. 148, 1567\u20131581 (2020)","journal-title":"Proc. Am. Math. Soc."},{"issue":"5","key":"1532_CR54","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1007\/s11633-017-1054-2","volume":"14","author":"T Poggio","year":"2017","unstructured":"Poggio, T., Mhaskar, H., Rosasco, L., Miranda, B., Liao, Q.: Why and when can deep-but not shallow-networks avoid the curse of dimensionality: a review. Int. J. Autom. Comput. 14(5), 503\u2013519 (2017)","journal-title":"Int. J. Autom. Comput."},{"key":"1532_CR55","unstructured":"Powell, C., Lord, G., Shardlow, T.: An Introduction to Computational Stochastic PDEs, 1 edn, bol. 8. Texts in Applied Mathematics. Cambridge University Press, London (2014)"},{"key":"1532_CR56","doi-asserted-by":"crossref","unstructured":"Quarteroni, A., Manzoni, A., Negri, F.: Reduced basis methods for partial differential equations, volume\u00a092 of Unitext. Springer, Cham (2016). An introduction, La Matematica per il 3+2","DOI":"10.1007\/978-3-319-15431-2"},{"key":"1532_CR57","doi-asserted-by":"crossref","unstructured":"Raissi, M.: Deep hidden physics models: deep learning of nonlinear partial differential equations. arXiv preprint arXiv:1801.06637 (2018)","DOI":"10.1016\/j.jcp.2017.11.039"},{"key":"1532_CR58","unstructured":"Raissi, M., Perdikaris, P., Karniadakis, G.E.: Physics informed deep learning (part i): data-driven solutions of nonlinear partial differential equations. arXiv preprint arXiv:1711.10561 (2017)"},{"key":"1532_CR59","unstructured":"Raissi, M., Perdikaris, P., Karniadakis, G.E.: Physics informed deep learning (part ii): data-driven discovery of nonlinear partial differential equations. arxiv. arXiv preprint arXiv:1711.10561, (2017)"},{"key":"1532_CR60","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1090\/mcom\/3113","volume":"86","author":"H Rauhut","year":"2014","unstructured":"Rauhut, H., Schwab, C.: Compressive sensing Petrov\u2013Galerkin approximation of high-dimensional parametric operator equations. Math. Comput. 86, 661\u2013700 (2014)","journal-title":"Math. Comput."},{"key":"1532_CR61","doi-asserted-by":"publisher","first-page":"108852","DOI":"10.1016\/j.jcp.2019.07.050","volume":"397","author":"F Regazzoni","year":"2019","unstructured":"Regazzoni, F., Ded\u00e8, L., Quarteroni, A.: Machine learning for fast and reliable solution of time-dependent differential equations. J. Comput. Phys. 397, 108852 (2019)","journal-title":"J. Comput. Phys."},{"issue":"3","key":"1532_CR62","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/s11831-008-9019-9","volume":"15","author":"G Rozza","year":"2008","unstructured":"Rozza, G., Huynh, D.B.P., Patera, A.T.: Reduced basis approximation and a posteriori error estimation for affinely parametrized elliptic coercive partial differential equations: application to transport and continuum mechanics. Arch. Comput. Methods Eng. 15(3), 229\u2013275 (2008)","journal-title":"Arch. Comput. Methods Eng."},{"key":"1532_CR63","doi-asserted-by":"crossref","unstructured":"Samaniego, E., Anitescu, C., Goswami, S., Nguyen-Thanh, V.M., Guo, H., Hamdia, K., Rabczuk, T., Zhuang, X.: An energy approach to the solution of partial differential equations in computational mechanics via machine learning: concepts, implementation and applications. arXiv preprint arXiv:1908.10407 (2019)","DOI":"10.1016\/j.cma.2019.112790"},{"key":"1532_CR64","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/j.cnsns.2019.04.025","volume":"77","author":"O San","year":"2019","unstructured":"San, O., Maulik, R., Ahmed, M.: An artificial neural network framework for reduced order modeling of transient flows. Commun. Nonlinear Sci. Numer. Simul. 77, 271\u2013287 (2019)","journal-title":"Commun. Nonlinear Sci. Numer. Simul."},{"issue":"1","key":"1532_CR65","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1142\/S0219530518500203","volume":"17","author":"C Schwab","year":"2019","unstructured":"Schwab, C., Zech, J.: Deep learning in high dimension: Neural network expression rates for generalized polynomial chaos expansions in UQ. Anal. Appl. (Singap.) 17(1), 19\u201355 (2019)","journal-title":"Anal. Appl. (Singap.)"},{"issue":"24","key":"1532_CR66","doi-asserted-by":"publisher","first-page":"241722","DOI":"10.1063\/1.5019779","volume":"148","author":"KT Sch\u00fctt","year":"2018","unstructured":"Sch\u00fctt, K.T., Sauceda, H.E., Kindermans, P.-J., Tkatchenko, A., M\u00fcller, K.-R.: SchNet\u2014a deep learning architecture for molecules and materials. J. Chem. Phys. 148(24), 241722 (2018)","journal-title":"J. Chem. Phys."},{"issue":"3","key":"1532_CR67","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1016\/j.acha.2016.04.003","volume":"44","author":"U Shaham","year":"2018","unstructured":"Shaham, U., Cloninger, A., Coifman, R.R.: Provable approximation properties for deep neural networks. Appl. Comput. Harmon. Anal. 44(3), 537\u2013557 (2018)","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"1532_CR68","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1016\/j.jcp.2018.08.029","volume":"375","author":"J Sirignano","year":"2018","unstructured":"Sirignano, J., Spiliopoulos, K.: DGM: A deep learning algorithm for solving partial differential equations. J. Comput. Phys. 375, 1339\u20131364 (2018)","journal-title":"J. Comput. Phys."},{"key":"1532_CR69","doi-asserted-by":"publisher","first-page":"02","DOI":"10.1016\/j.jcp.2018.08.036","volume":"375","author":"R Tripathy","year":"2018","unstructured":"Tripathy, R., Bilionis, I.: Deep UQ: learning deep neural network surrogate models for high dimensional uncertainty quantification. J. Comput. Phys. 375, 02 (2018)","journal-title":"J. Comput. Phys."},{"key":"1532_CR70","volume-title":"Mathematical Statistics with Applications","author":"D Wackerly","year":"2014","unstructured":"Wackerly, D., Mendenhall, W., Scheaffer, R.: Mathematical Statistics with Applications, 7th edn. Cengage Learning, Boston (2014)","edition":"7"},{"key":"1532_CR71","doi-asserted-by":"crossref","first-page":"2025","DOI":"10.1051\/m2an\/2019048","volume":"53","author":"C Webster","year":"2019","unstructured":"Webster, C., Tran, H., Dexter, N.: A mixed $$\\ell _1$$ regularization approach for sparse simultaneous approximation of parameterized PDEs. ESAIM Math. Model. Numer. 53, 2025\u20132045 (2019)","journal-title":"ESAIM Math. Model. Numer."},{"issue":"4","key":"1532_CR72","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1007\/s40304-017-0117-6","volume":"5","author":"E Weinan","year":"2017","unstructured":"Weinan, E., Han, J., Jentzen, A.: Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations. Commun. Math. Stat. 5(4), 349\u2013380 (2017)","journal-title":"Commun. Math. Stat."},{"issue":"1","key":"1532_CR73","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40304-018-0127-z","volume":"6","author":"E Weinan","year":"2018","unstructured":"Weinan, E., Yu, B.: The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems. Commun. Math. Stat. 6(1), 1\u201312 (2018)","journal-title":"Commun. Math. Stat."},{"key":"1532_CR74","unstructured":"Yang, Y., Perdikaris, P.: Physics-informed deep generative models. arXiv preprint arXiv:1812.03511 (2018)"},{"key":"1532_CR75","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.neunet.2017.07.002","volume":"94","author":"D Yarotsky","year":"2017","unstructured":"Yarotsky, D.: Error bounds for approximations with deep ReLU networks. Neural Netw. 94, 103\u2013114 (2017)","journal-title":"Neural Netw."},{"key":"1532_CR76","unstructured":"Yarotsky, D.: Optimal approximation of continuous functions by very deep ReLU networks. arXiv preprint arXiv:1802.03620 (2018)"},{"key":"1532_CR77","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/j.neunet.2020.01.018","volume":"124","author":"D-X Zhou","year":"2020","unstructured":"Zhou, D.-X.: Theory of deep convolutional neural networks: downsampling. Neural Netw. 124, 319\u2013327 (2020)","journal-title":"Neural Netw."}],"container-title":["Journal of Scientific Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10915-021-01532-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10915-021-01532-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10915-021-01532-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T00:10:11Z","timestamp":1666829411000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10915-021-01532-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,5]]},"references-count":77,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["1532"],"URL":"https:\/\/doi.org\/10.1007\/s10915-021-01532-w","relation":{},"ISSN":["0885-7474","1573-7691"],"issn-type":[{"value":"0885-7474","type":"print"},{"value":"1573-7691","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,5]]},"assertion":[{"value":"27 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"22"}}