Characteristic kernels on Hilbert spaces, Banach spaces, and on sets of measures

2022/06/15 by Johanna F. Ziegel, Ziegel, Johanna, David Ginsbourger +3 · 2 citations
Mathematics · #Advanced Harmonic Analysis Research #Analytic and geometric function theory #Advanced Banach Space Theory

paper · pdf · doi:10.48550/arxiv.2206.07588

Abstract

We present new classes of positive definite kernels on non-standard spaces that are integrally strictly positive definite or characteristic. In particular, we discuss radial kernels on separable Hilbert spaces, and introduce broad classes of kernels on Banach spaces and on metric spaces of strong negative type. The general results are used to give explicit classes of kernels on separable L^p spaces and on sets of measures.

Cited by

• Uncertainty Quantification for Regression: A Unified Framework based on kernel scores
• Quantum-inspired probability metrics define a complete, universal space for statistical learning

Related

• Reproducing kernels and choices of associated feature spaces, in the form of L²-spaces
• New characterizations of reproducing kernel Hilbert spaces and\n applications to metric geometry
• Strictly positive definite kernels on compact Riemannian manifolds
• Operator valued positive definite kernels and differentiable universality
• Strictly positive definite kernels on two-point compact homogeneous spaces