Efficient approximation of high-dimensional functions with neural networks

9 Dec 2019  ·  Patrick Cheridito, Arnulf Jentzen, Florian Rossmannek ·

In this paper, we develop a framework for showing that neural networks can overcome the curse of dimensionality in different high-dimensional approximation problems. Our approach is based on the notion of a catalog network, which is a generalization of a standard neural network in which the nonlinear activation functions can vary from layer to layer as long as they are chosen from a predefined catalog of functions. As such, catalog networks constitute a rich family of continuous functions. We show that under appropriate conditions on the catalog, catalog networks can efficiently be approximated with rectified linear unit-type networks and provide precise estimates on the number of parameters needed for a given approximation accuracy. As special cases of the general results, we obtain different classes of functions that can be approximated with ReLU networks without the curse of dimensionality.

PDF Abstract
No code implementations yet. Submit your code now

Categories


Numerical Analysis Numerical Analysis 68T07 I.2.0