A Theoretical Analysis of Deep Neural Networks and Parametric PDEs
Top Cited Papers
Open Access
- 2 June 2021
- journal article
- research article
- Published by Springer Nature in Constructive Approximation
- Vol. 55 (1) , 73-125
Abstract
We derive upper bounds on the complexity of ReLU neural networks approximating the solution maps of parametric partial differential equations. In particular, without any knowledge of its concrete shape, we use the inherent low dimensionality of the solution manifold to obtain approximation rates which are significantly superior to those provided by classical neural network approximation results. Concretely, we use the existence of a small reduced basis to construct, for a large variety of parametric partial differential equations, neural networks that yield approximations of the parametric solution maps in such a way that the sizes of these networks essentially only depend on the size of the reduced basis.Keywords
All Related Versions
Funding Information
- University of Vienna
This publication has 53 references indexed in Scilit:
- Convergence Rates for Greedy Algorithms in Reduced Basis MethodsSIAM Journal on Mathematical Analysis, 2011
- Efficient reduced-basis treatment of nonaffine and nonlinear partial differential equationsESAIM: Mathematical Modelling and Numerical Analysis, 2007
- On the mathematical foundations of learningBulletin of the American Mathematical Society, 2001
- Lower bounds for approximation by MLP neural networksNeurocomputing, 1999
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Neural Networks for Optimal Approximation of Smooth and Analytic FunctionsNeural Computation, 1996
- Universal approximation bounds for superpositions of a sigmoidal functionIEEE Transactions on Information Theory, 1993
- Approximation properties of a multilayered feedforward artificial neural networkAdvances in Computational Mathematics, 1993
- Recent advances in reduction methods for nonlinear problemsComputers & Structures, 1981
- An approximate analysis technique for design calculationsAIAA Journal, 1971