Salvato in:
Dettagli Bibliografici
Autori principali: Germain, Thibaut, Flamary, Rémi, Kostic, Vladimir R., Lounici, Karim
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.24920
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912615138066432
author Germain, Thibaut
Flamary, Rémi
Kostic, Vladimir R.
Lounici, Karim
author_facet Germain, Thibaut
Flamary, Rémi
Kostic, Vladimir R.
Lounici, Karim
contents The geometry of dynamical systems estimated from trajectory data is a major challenge for machine learning applications. Koopman and transfer operators provide a linear representation of nonlinear dynamics through their spectral decomposition, offering a natural framework for comparison. We propose a novel approach representing each system as a distribution of its joint operator eigenvalues and spectral projectors and defining a metric between systems leveraging optimal transport. The proposed metric is invariant to the sampling frequency of trajectories. It is also computationally efficient, supported by finite-sample convergence guarantees, and enables the computation of Fréchet means, providing interpolation between dynamical systems. Experiments on simulated and real-world datasets show that our approach consistently outperforms standard operator-based distances in machine learning applications, including dimensionality reduction and classification, and provides meaningful interpolation between dynamical systems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24920
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Spectral-Grassmann Wasserstein metric for operator representations of dynamical systems
Germain, Thibaut
Flamary, Rémi
Kostic, Vladimir R.
Lounici, Karim
Machine Learning
The geometry of dynamical systems estimated from trajectory data is a major challenge for machine learning applications. Koopman and transfer operators provide a linear representation of nonlinear dynamics through their spectral decomposition, offering a natural framework for comparison. We propose a novel approach representing each system as a distribution of its joint operator eigenvalues and spectral projectors and defining a metric between systems leveraging optimal transport. The proposed metric is invariant to the sampling frequency of trajectories. It is also computationally efficient, supported by finite-sample convergence guarantees, and enables the computation of Fréchet means, providing interpolation between dynamical systems. Experiments on simulated and real-world datasets show that our approach consistently outperforms standard operator-based distances in machine learning applications, including dimensionality reduction and classification, and provides meaningful interpolation between dynamical systems.
title A Spectral-Grassmann Wasserstein metric for operator representations of dynamical systems
topic Machine Learning
url https://arxiv.org/abs/2509.24920