Learning Koopman-based Stability Certificates for Unknown Nonlinear Systems

Koopman operator theory has gained significant attention in recent years for identifying discrete-time nonlinear systems by embedding them into an infinite-dimensional linear vector space. However, providing stability guarantees while learning the continuous-time dynamics, especially under conditions of relatively low observation frequency, remains a challenge within the existing Koopman-based learning frameworks. To address this challenge, we propose an algorithmic framework to simultaneously learn the vector field and Lyapunov functions for unknown nonlinear systems, using a limited amount of data sampled across the state space and along the trajectories at a relatively low sampling frequency. The proposed framework builds upon recently developed high-accuracy Koopman generator learning for capturing transient system transitions and physics-informed neural networks for training Lyapunov functions. We show that the learned Lyapunov functions can be formally verified using a satisfiability modulo theories (SMT) solver and provide less conservative estimates of the region of attraction compared to existing methods.

A Generalized Nyquist-Shannon Sampling Theorem Using the Koopman Operator

The sampling theorem plays a fundamental role for the recovery of continuous-time signals from discrete-time samples in the field of signal processing. The sampling theorem of non-band-limited signals has evolved into one of the most challenging problems. In this work, a generalized sampling theorem -- which builds on the Koopman operator -- is proved for signals in generator-bounded space (Theorem 1). It naturally extends the Nyquist-Shannon sampling theorem that, 1) for band-limited signals, the lower bounds of sampling frequency given by these two theorems are exactly the same; 2) the Koopman operator-based sampling theorem can also provide finite bound of sampling frequency for certain types of non-band-limited signals, which can not be addressed by Nyquist-Shannon sampling theorem. These types of non-band-limited signals include but not limited to, for example, inverse Laplace transform with limited imaginary interval of integration, and linear combinations of complex exponential functions. Moreover, the Koopman operator-based reconstruction algorithm is provided with theoretical result of convergence. By this algorithm, the sampling theorem is effectively illustrated on several signals related to sine, exponential and polynomial signals.