Constrained physical-statistics models for dynamical system identification and prediction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Constrained physical-statistics models for dynamical system identification and prediction

Résumé

Modeling dynamical systems combining prior physical knowledge and machinelearning (ML) is promising in scientific problems when the underlying processesare not fully understood, e.g. when the dynamics is partially known. A commonpractice to identify the respective parameters of the physical and ML componentsis to formulate the problem as supervised learning on observed trajectories.However, this formulation leads to an infinite number of possible decompositions.To solve this ill-posedness, we reformulate the learning problem by introducingan upper bound on the prediction error of a physical-statistical model. This allowsus to control the contribution of both the physical and statistical componentsto the overall prediction. This framework generalizes several existing hybridschemes proposed in the literature. We provide theoretical guarantees on the wellposednessof our formulation along with a proof of convergence in a simple affinesetting. For more complex dynamics, we validate our framework experimentally
Fichier principal
Vignette du fichier
Dona_ICLR_2022.pdf (1.51 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03739574 , version 1 (27-07-2022)

Identifiants

  • HAL Id : hal-03739574 , version 1

Citer

Jérémie Donà, Marie Déchelle, Marina Lévy, Patrick Gallinari. Constrained physical-statistics models for dynamical system identification and prediction. ICLR 2022 - The Tenth International Conference on Learning Representations, Apr 2022, virtual event, France. ⟨hal-03739574⟩
226 Consultations
126 Téléchargements

Partager

Gmail Facebook X LinkedIn More