Generic controllability of equivariant systems and applications to particle systems and neural networks - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Generic controllability of equivariant systems and applications to particle systems and neural networks

Résumé

There exist many examples of systems which have some symmetries, and which one may monitor with symmetry preserving controls. Since symmetries are preserved along the evolution, full controllability is not possible, and controllability has to be considered inside sets of states with same symmetries. We prove that generic systems with symmetries are controllable in this sense. This result has several applications, for instance: (i) generic controllability of particle systems when the kernel of interaction between particles plays the role of a mean-field control; (ii) generic controllability for families of vector fields on manifolds with boundary; (iii) universal interpolation for neural networks architectures with ``generic" self attention-type layers - a type of layers ubiquitous in recent neural networks architectures, e.g., in the Transformers architecture. The tools we develop could help address various other questions of control of equivariant systems.
Fichier principal
Vignette du fichier
Generic control of equivariant systems v15.pdf (503.08 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04542990 , version 1 (11-04-2024)

Identifiants

  • HAL Id : hal-04542990 , version 1

Citer

Andrei Agrachev, Cyril Letrouit. Generic controllability of equivariant systems and applications to particle systems and neural networks. 2024. ⟨hal-04542990⟩
0 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More