First-order conditions for the optimal control of learning-informed nonsmooth PDEs

arXiv2206.00297MaRDI QIDQ6400770FDOQ6400770

Authors: Guozhi Dong, Michael Hintermüller, Kostas Papafitsoros, Kathrin Völkner 

Publication date: 1 June 2022

Abstract: In this paper we study the optimal control of a class of semilinear elliptic partial differential equations which have nonlinear constituents that are only accessible by data and are approximated by nonsmooth ReLU neural networks. The optimal control problem is studied in detail. In particular, the existence and uniqueness of the state equation are shown, and continuity as well as directional differentiability properties of the corresponding control-to-state map are established. Based on approximation capabilities of the pertinent networks, we address fundamental questions regarding approximating properties of the learning-informed control-to-state map and the solution of the corresponding optimal control problem. Finally, several stationarity conditions are derived based on different notions of generalized differentiability.

This page was built for publication: First-order conditions for the optimal control of learning-informed nonsmooth PDEs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6400770)