Overcoming the curse of dimensionality for approximating Lyapunov functions with deep neural networks under a small-gain condition

arXiv2001.08423MaRDI QIDQ6333360FDOQ6333360

Authors: Lars Grüne 

Publication date: 23 January 2020

Abstract: We propose a deep neural network architecture for storing approximate Lyapunov functions of systems of ordinary differential equations. Under a small-gain condition on the system, the number of neurons needed for an approximation of a Lyapunov function with fixed accuracy grows only polynomially in the state dimension, i.e., the proposed approach is able to overcome the curse of dimensionality.

This page was built for publication: Overcoming the curse of dimensionality for approximating Lyapunov functions with deep neural networks under a small-gain condition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6333360)