The kernel mean embedding of a random probability distribution and its principal components

Abstract

Given a random probability distribution \(F\), whose realizations are defined on \(\mathbb R^d\), and a kernel \(k\), our aim is to analyze the properties of the kernel mean embedding, \(\mu_F\), of \(F\) as a random element of the corresponding reproducing kernel Hilbert space \(\mathcal H\). This establishes a rigorous framework in which kernel statistical techniques for distributional data can be stated both in the sample and population settings and, thus, the asymptotic properties of sample procedures can be properly established. As an illustration of this approach we focus on the principal components of \(F\). We obtain a general convergence result and the explicit expression of the spectral decomposition for the uncentered covariance operator of a normal probability distribution with a Gaussian distributed expectation. The performance of this kernel principal components procedure is illustrated with simulations and the analysis of the intensity distribution in synthetic aperture radar images.