Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jaffe, Sean, Davydov, Alexander, Lapsekili, Deniz, Singh, Ambuj, Bullo, Francesco
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910776411815936
author Jaffe, Sean
Davydov, Alexander
Lapsekili, Deniz
Singh, Ambuj
Bullo, Francesco
author_facet Jaffe, Sean
Davydov, Alexander
Lapsekili, Deniz
Singh, Ambuj
Bullo, Francesco
contents Global stability and robustness guarantees in learned dynamical systems are essential to ensure well-behavedness of the systems in the face of uncertainty. We present Extended Linearized Contracting Dynamics (ELCD), the first neural network-based dynamical system with global contractivity guarantees in arbitrary metrics. The key feature of ELCD is a parametrization of the extended linearization of the nonlinear vector field. In its most basic form, ELCD is guaranteed to be (i) globally exponentially stable, (ii) equilibrium contracting, and (iii) globally contracting with respect to some metric. To allow for contraction with respect to more general metrics in the data space, we train diffeomorphisms between the data space and a latent space and enforce contractivity in the latent space, which ensures global contractivity in the data space. We demonstrate the performance of ELCD on the high dimensional LASA, multi-link pendulum, and Rosenbrock datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2402_08090
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees
Jaffe, Sean
Davydov, Alexander
Lapsekili, Deniz
Singh, Ambuj
Bullo, Francesco
Machine Learning
Optimization and Control
Global stability and robustness guarantees in learned dynamical systems are essential to ensure well-behavedness of the systems in the face of uncertainty. We present Extended Linearized Contracting Dynamics (ELCD), the first neural network-based dynamical system with global contractivity guarantees in arbitrary metrics. The key feature of ELCD is a parametrization of the extended linearization of the nonlinear vector field. In its most basic form, ELCD is guaranteed to be (i) globally exponentially stable, (ii) equilibrium contracting, and (iii) globally contracting with respect to some metric. To allow for contraction with respect to more general metrics in the data space, we train diffeomorphisms between the data space and a latent space and enforce contractivity in the latent space, which ensures global contractivity in the data space. We demonstrate the performance of ELCD on the high dimensional LASA, multi-link pendulum, and Rosenbrock datasets.
title Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2402.08090