Control Forward-Backward Consistency: Quantifying the Accuracy of Koopman Control Family Models
For researchers using data-driven Koopman models in control, this provides a practical, closed-form error bound that was previously unavailable, though the extension is incremental.
This paper extends the forward-backward consistency index to control systems, providing a closed-form error bound for Koopman Control Family models. The main result shows that the relative root-mean-square error is bounded by the square root of the control consistency index, enabling sharp, computable accuracy quantification.
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.