Invariance of Gaussian RKHSs under Koopman operators of stochastic differential equations with constant matrix coefficients

TL;DR

This paper investigates the invariance of Gaussian RKHSs under Koopman operators associated with linear stochastic differential equations, establishing a Lyapunov-like condition for invariance and exploring the inclusion relations between different Gaussian RKHSs.

Contribution

It provides a Lyapunov-like matrix inequality condition ensuring Gaussian RKHS invariance under Koopman operators for linear SDEs with constant coefficients.

Findings

Invariance of Gaussian RKHSs under Koopman operators is characterized by a specific matrix inequality.

A characterization of inclusion relations between Gaussian RKHSs is established.

The necessity of the Lyapunov-like condition remains an open problem.

Abstract

We consider the Koopman operator semigroup $(K^t)_{t\ge 0}$ associated with stochastic differential equations of the form $dX_t = AX_t\,dt + B\,dW_t$ with constant matrices $A$ and $B$ and Brownian motion $W_t$. We prove that the reproducing kernel Hilbert space $\bH_C$ generated by a Gaussian kernel with a positive definite covariance matrix $C$ is invariant under each Koopman operator $K^t$ if the matrices $A$, $B$, and $C$ satisfy the following Lyapunov-like matrix inequality: $AC^2 + C^2A^\top\le 2BB^\top$. In this course, we prove a characterization concerning the inclusion $\bH_{C_1}\subset\bH_{C_2}$ of Gaussian RKHSs for two positive definite matrices $C_1$ and $C_2$. The question of whether the sufficient Lyapunov-condition is also necessary is left as an open problem.