Finite-time Koopman Identifier: A Unified Batch-online Learning Framework for Joint Learning of Koopman Structure and Parameters

TL;DR

This paper introduces a unified batch-online learning framework for Koopman operator-based system identification, ensuring finite-time convergence and optimizing observable functions using Bayesian methods.

Contribution

It proposes a novel incremental Koopman update law with finite-time convergence guarantees and integrates a Bayesian optimization approach for selecting optimal observables.

Findings

Finite-time convergence under rank conditions.

Sub-linear growth of identification regret.

Effective selection of observable functions via Bayesian optimization.

Abstract

In this paper, a unified batch-online learning approach is introduced to learn a linear representation of nonlinear system dynamics using the Koopman operator. The presented system modeling approach leverages a novel incremental Koopman-based update law that retrieves a mini-batch of samples stored in a memory to not only minimizes the instantaneous Koopman operator's identification errors but also the identification errors for the batch of retrieved samples. Discontinuous modifications of gradient flows are presented for the online update law to assure finite-time convergence under easy-to-verify conditions defined on the batch of data. Therefore, this unified online-batch framework allows performing joint sample- and time-domain analysis for converging the Koopman operator's parameters. More specifically, it is shown that if the collected mini-batch of samples guarantees a rank condition, then finite-time guarantee in the time domain can be certified and the settling time depends on the quality of collected samples being reused in the update law. Moreover, the efficiency of the proposed Koopman-based update law is further analyzed by showing that the identification regret in continuous time grows sub-linearly with time. Furthermore, to avoid learning corrupted dynamics due to the selection of an inappropriate set of Koopman observables, a higher-layer meta learner employs a discrete Bayesian optimization algorithm to obtain the best library of observable functions for the operator. Since finite-time convergence of the Koopman model for each set of observable is guaranteed under a rank condition on stored data, the fitness of each set of observables can be obtained based on the identification error on the stored samples in the proposed framework and even without implementing any controller based on the learned system.