Control Forward-Backward Consistency: Quantifying the Accuracy of Koopman Control Family Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Haseli, Masih, Cortés, Jorge, Burdick, Joel W.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910102436446208
author Haseli, Masih
Cortés, Jorge
Burdick, Joel W.
author_facet Haseli, Masih
Cortés, Jorge
Burdick, Joel W.
contents This paper extends the forward-backward consistency index, originally introduced in Koopman modeling of systems without input, to the setting of control systems, providing a closed-form computable measure of accuracy for data-driven models associated with the Koopman Control Family (KCF). Building on a forward-backward regression perspective, we introduce the control forward-backward consistency matrix and demonstrate that it possesses several favorable properties. Our main result establishes that the relative root-mean-square error of KCF function predictors is strictly bounded by the square root of the control consistency index, defined as the maximum eigenvalue of the consistency matrix. This provides a sharp, closed-form computable error bound for finite-dimensional KCF models. We further specialize this bound to the widely used lifted linear and bilinear models. We also discuss how the control consistency index can be incorporated into optimization-based modeling and illustrate the methodology via simulations.
format Preprint
id arxiv_https___arxiv_org_abs_2603_27548
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Control Forward-Backward Consistency: Quantifying the Accuracy of Koopman Control Family Models
Haseli, Masih
Cortés, Jorge
Burdick, Joel W.
Optimization and Control
Systems and Control
This paper extends the forward-backward consistency index, originally introduced in Koopman modeling of systems without input, to the setting of control systems, providing a closed-form computable measure of accuracy for data-driven models associated with the Koopman Control Family (KCF). Building on a forward-backward regression perspective, we introduce the control forward-backward consistency matrix and demonstrate that it possesses several favorable properties. Our main result establishes that the relative root-mean-square error of KCF function predictors is strictly bounded by the square root of the control consistency index, defined as the maximum eigenvalue of the consistency matrix. This provides a sharp, closed-form computable error bound for finite-dimensional KCF models. We further specialize this bound to the widely used lifted linear and bilinear models. We also discuss how the control consistency index can be incorporated into optimization-based modeling and illustrate the methodology via simulations.
title Control Forward-Backward Consistency: Quantifying the Accuracy of Koopman Control Family Models
topic Optimization and Control
Systems and Control
url https://arxiv.org/abs/2603.27548