Feedback maximum principle for ensemble control of local continuity equations. An application to supervised machine learning

DOI10.1109/LCSYS.2021.3089139arXiv2105.04248MaRDI QIDQ6367252FDOQ6367252

Authors: Maxim Staritsyn, N. Pogodaev, R. A. Chertovskih, Fernando Lobo Pereira 

Publication date: 10 May 2021

Abstract: We consider an optimal control problem for a system of local continuity equations on a space of probability measures. Such systems can be viewed as macroscopic models of ensembles of non-interacting particles or homotypic individuals, representing several different ``populations. For the stated problem, we propose a necessary optimality condition, which involves feedback controls inherent to the extremal structure, designed via the standard Pontryagin's Maximum Principle conditions. This optimality condition admits a realization as an iterative algorithm for optimal control. As a motivating case, we discuss an application of the derived optimality condition and the consequent numeric method to a problem of supervised machine learning via dynamic systems.

This page was built for publication: Feedback maximum principle for ensemble control of local continuity equations. An application to supervised machine learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6367252)