A Theoretical Analysis of Deep Neural Networks and Parametric PDEs
Preprint
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 approximation results. We use this low dimensionality to guarantee the existence of a reduced basis. Then, for a large variety of parametric partial differential equations, we construct neural networks that yield approximations of the parametric maps not suffering from a curse of dimension and essentially only depending on the size of the reduced basis.Keywords
All Related Versions
This publication has 48 references indexed in Scilit:
- DNN Expression Rate Analysis of High-Dimensional PDEs: Application to Option PricingConstructive Approximation, 2021
- Variational Monte Carlo—bridging concepts of machine learning and high-dimensional partial differential equationsAdvances in Computational Mathematics, 2019
- Deep Learning-Based Numerical Methods for High-Dimensional Parabolic Partial Differential Equations and Backward Stochastic Differential EquationsCommunications in Mathematics and Statistics, 2017
- Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A reviewInternational Journal of Automation and Computing, 2017
- Adaptive stochastic Galerkin FEM with hierarchical tensor representationsNumerische Mathematik, 2016
- Tensor Networks and Hierarchical Tensors for the Solution of High-Dimensional Partial Differential EquationsFoundations of Computational Mathematics, 2016
- Greedy Algorithms for Reduced Bases in Banach SpacesConstructive Approximation, 2013
- PARAMETRIC FAMILIES OF REDUCED FINITE ELEMENT MODELS. THEORY AND APPLICATIONSMechanical Systems and Signal Processing, 1996
- Approximation properties of a multilayered feedforward artificial neural networkAdvances in Computational Mathematics, 1993
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989