We study embeddings of continuous dynamical systems in larger dimensions via projector operators. We call this technique PEDS, projective embedding of dynamical systems, as the stable fixed point of the original system dynamics are recovered via projection from the higher dimensional space. In this paper we provide a general definition and prove that for a particular type of rank-1 projector operator, the uniform mean field projector, the equations of motion become a mean field approximation of the dynamical system. While in general the embedding depends on a specified variable ordering, the same is not true for the uniform mean field projector. We prove a variety of results on the relationship between the spectrum of the Jacobian for fixed points in the original and in the embedded system. Direct applications of PEDS can be non-convex optimization and machine learning.

Projective embedding of dynamical systems: Uniform mean field equations / Caravelli, F.; Traversa, F. L.; Bonnin, M.; Bonani, F.. - In: PHYSICA D-NONLINEAR PHENOMENA. - ISSN 0167-2789. - ELETTRONICO. - 450:(2023). [10.1016/j.physd.2023.133747]

Projective embedding of dynamical systems: Uniform mean field equations

Traversa, F. L.;Bonnin, M.;Bonani, F.
2023

Abstract

We study embeddings of continuous dynamical systems in larger dimensions via projector operators. We call this technique PEDS, projective embedding of dynamical systems, as the stable fixed point of the original system dynamics are recovered via projection from the higher dimensional space. In this paper we provide a general definition and prove that for a particular type of rank-1 projector operator, the uniform mean field projector, the equations of motion become a mean field approximation of the dynamical system. While in general the embedding depends on a specified variable ordering, the same is not true for the uniform mean field projector. We prove a variety of results on the relationship between the spectrum of the Jacobian for fixed points in the original and in the embedded system. Direct applications of PEDS can be non-convex optimization and machine learning.
File in questo prodotto:
File Dimensione Formato  
PhysicaD 23.pdf

accesso riservato

Descrizione: Lavoro principale
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 2.31 MB
Formato Adobe PDF
2.31 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
PEDS.pdf

embargo fino al 26/04/2025

Descrizione: Versione post referee
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Creative commons
Dimensione 1.83 MB
Formato Adobe PDF
1.83 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2978294