Feedback Maximum Principle for Ensemble Control of Local Continuity Equations: An Application to Supervised Machine Learning

• Tipo: Artigo em Revista Científica Internacional
• Data: 2022

Autores

Staritsyn, M (Autor) FEUP; Nikolay Pogodaev (Autor) Outra; Roman Chertovskih (Autor) FEUP; Fernando Lobo Pereira (Autor) FEUP

Revista

Título: IEEE Control Systems Letters

Vol. 6

Páginas: 1046-1051

Editora: IEEE

Indexação

ISI Web of Knowledge - 5 Citações

Scopus - 7 Citações

Outras Informações

ID Authenticus: P-00V-28R

DOI: 10.1109/lcsys.2021.3089139

Abstract (EN): 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 conditions of optimality which involve feedback controls inherent to the extremal structure designed via the standard Pontryagin's Maximum Principle. These optimality conditions admit 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.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 6