Singular Value Decomposition of Operators on Reproducing Kernel Hilbert Spaces

by   Mattes Mollenhauer, et al.

Reproducing kernel Hilbert spaces (RKHSs) play an important role in many statistics and machine learning applications ranging from support vector machines to Gaussian processes and kernel embeddings of distributions. Operators acting on such spaces are, for instance, required to embed conditional probability distributions in order to implement the kernel Bayes rule and build sequential data models. It was recently shown that transfer operators such as the Perron-Frobenius or Koopman operator can also be approximated in a similar fashion using covariance and cross-covariance operators and that eigenfunctions of these operators can be obtained by solving associated matrix eigenvalue problems. The goal of this paper is to provide a solid functional analytic foundation for the eigenvalue decomposition of RKHS operators and to extend the approach to the singular value decomposition. The results are illustrated with simple guiding examples.


page 1

page 2

page 3

page 4


Eigendecompositions of Transfer Operators in Reproducing Kernel Hilbert Spaces

Transfer operators such as the Perron-Frobenius or Koopman operator play...

A Rigorous Theory of Conditional Mean Embeddings

Conditional mean embeddings (CME) have proven themselves to be a powerfu...

Composition operators on reproducing kernel Hilbert spaces with analytic positive definite functions

Composition operators have been extensively studied in complex analysis,...

Frame Decompositions of Bounded Linear Operators in Hilbert Spaces with Applications in Tomography

We consider the decomposition of bounded linear operators on Hilbert spa...

Hilbert Space Embeddings of POMDPs

A nonparametric approach for policy learning for POMDPs is proposed. The...


This article addresses several longstanding misconceptions concerning Ko...

Conditional expectation using compactification operators

The separate tasks of denoising, conditional expectation and manifold le...

Please sign up or login with your details

Forgot password? Click here to reset