Extension of First-Order Stable Spline Kernel to Encode Relative Degree

Abstract

This paper focuses on the kernel-based system identification methods, which estimate the impulse response of the target system in the Bayesian estimation framework. This paper discusses about continuous-time systems, and proposes a new kernel based on a prior that the relative degree of the target system is higher than or equal to two. Such a prior is identical to a prior on the continuity of the impulse response at time zero. The proposed kernel is an extension of the first-order Stable Spline kernel, which is one of the most famous kernels. Numerical examples are shown to demonstrate the effectiveness of the proposed kernel.