Back to Search Start Over

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

Authors :
Staritsyn, Maxim
Pogodaev, Nikolay
Chertovskih, Roman
Pereira, Fernando Lobo
Source :
IEEE Control Systems Letters, vol. 6, pp. 1046-1051, 2022
Publication Year :
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.

Details

Database :
arXiv
Journal :
IEEE Control Systems Letters, vol. 6, pp. 1046-1051, 2022
Publication Type :
Report
Accession number :
edsarx.2105.04248
Document Type :
Working Paper
Full Text :
https://doi.org/10.1109/LCSYS.2021.3089139