Nonparametric Sparse Online Learning of the Koopman Operator
This work addresses the limitation of batch data reliance in Koopman operator learning, offering an online method for applications like control or prediction where data arrive over time.
The authors tackled the problem of learning the Koopman operator for nonlinear dynamical systems from sequential data, presenting a sparse online algorithm with provable convergence guarantees and demonstrating its capability in numerical experiments.
The Koopman operator provides a powerful framework for representing the dynamics of general nonlinear dynamical systems. However, existing data-driven approaches to learning the Koopman operator rely on batch data. In this work, we present a sparse online learning algorithm that learns the Koopman operator iteratively via stochastic approximation, with explicit control over model complexity and provable convergence guarantees. Specifically, we study the Koopman operator via its action on the reproducing kernel Hilbert space (RKHS), and address the mis-specified scenario where the dynamics may escape the chosen RKHS. In this mis-specified setting, we relate the Koopman operator to the conditional mean embeddings (CME) operator. We further establish both asymptotic and finite-time convergence guarantees for our learning algorithm in mis-specified setting, with trajectory-based sampling where the data arrive sequentially over time. Numerical experiments demonstrate the algorithm's capability to learn unknown nonlinear dynamics.