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

DOI10.3150/23-BEJ1639arXiv2206.07588OpenAlexW4391458296WikidataQ128817781 ScholiaQ128817781MaRDI QIDQ6201859FDOQ6201859

Authors: Johanna F. Ziegel, D. Ginsbourger, Lutz Dümbgen 

Publication date: 26 March 2024

Published in: Bernoulli (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/2206.07588

zbMATH Keywords

characteristic kernelintegrally strictly positive definite kernelkernel on Banach spacekernel on Hilbert spacekernel on measures

Mathematics Subject Classification ID

Density estimation (62G07) Learning and adaptive systems in artificial intelligence (68T05) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Topological data analysis (62R40)

Cites Work

• Measuring and testing dependence by correlation of distances
• Equivalence of distance-based and RKHS-based statistics in hypothesis testing
• Strictly Proper Scoring Rules, Prediction, and Estimation
• Interpolation of spatial data. Some theory for kriging
• Ball divergence: nonparametric two sample test
• Distance covariance in metric spaces
• On a new multivariate two-sample test.
• Hilbert space embeddings and metrics on probability measures
• Support Vector Machines
• Title not available (Why is that?)
• An invitation to statistics in Wasserstein space
• Algorithmic Learning Theory
• A kernel two-sample test
• Title not available (Why is that?)
• A new test for multivariate normality
• Kernel methods in machine learning
• Brownian distance covariance
• Mercer's theorem on general domains: on the interaction between measures, kernels, and RKHSs
• On the influence of the kernel on the consistency of support vector machines
• Scattered Data Approximation
• Positive definite functions and generalizations, an historical survey
• Title not available (Why is that?)
• Measure and integration theory. Transl. from the German by Robert B. Burckel
• Gaussian Measures on Function Spaces
• Uniqueness theorems for measures in \(L_ r\) and \(C_ o(\Omega)\)
• Scoring Rules for Continuous Probability Distributions
• The geometry of proper scoring rules
• Bimeasurable functions
• Functional analysis
• Kernel distribution embeddings: universal kernels, characteristic kernels and kernel metrics on distributions
• The small ball theorem for Hilbert spaces
• Learning theory for distribution regression
• Distance covariance for stochastic processes
• Gaussian processes with multidimensional distribution inputs via optimal transport and Hilbertian embedding
• Strictly proper kernel scores and characteristic kernels on compact spaces

This page was built for publication: Characteristic kernels on Hilbert spaces, Banach spaces, and on sets of measures

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6201859)