On Gaussian kernels on Hilbert spaces and kernels on hyperbolic spaces
From MaRDI portal
(Redirected from Publication:2139169)
Abstract: This paper describes the concepts of Universal/ Integrally Strictly Positive Definite/ -Universal for the Gaussian kernel on a Hilbert space. As a consequence we obtain a similar characterization for an important family of kernels studied and developed by Schoenberg and also on a family of spatial-time kernels popular on geostatistics, the Gneiting class, and its generalizations. Either by using similar techniques, or by a direct consequence of the Gaussian kernel on Hilbert spaces, we characterize the same concepts for a family of kernels defined on a Hyperbolic space.
Recommendations
- Strictly positive definite kernels on the hilbert sphere
- Strictly positive definite kernels on compact two-point homogeneous spaces
- Universality, Characteristic Kernels and RKHS Embedding of Measures
- New characterizations of reproducing kernel Hilbert spaces and applications to metric geometry
- Operator-valued positive definite kernels and differentiable universality
Cites work
- scientific article; zbMATH DE number 5968915 (Why is no real title available?)
- scientific article; zbMATH DE number 4004880 (Why is no real title available?)
- scientific article; zbMATH DE number 1466451 (Why is no real title available?)
- scientific article; zbMATH DE number 3252860 (Why is no real title available?)
- A kernel two-sample test
- Approximation Theory and Harmonic Analysis on Spheres and Balls
- Dense Algebras of Functions in L p
- Distance functions for reproducing kernel Hilbert spaces
- Distances hilbertiennes invariantes sur un espace homogene
- Gneiting class, semi-metric spaces and isometric embeddings
- Hilbert space embeddings and metrics on probability measures
- Interpolation of scattered data: distance matrices and conditionally positive definite functions
- Kernel distribution embeddings: universal kernels, characteristic kernels and kernel metrics on distributions
- Learning Theory
- Matérn cross-covariance functions for multivariate random fields
- Nonseparable, Stationary Covariance Functions for Space–Time Data
- On the mathematical foundations of learning
- Operator-valued positive definite kernels and differentiable universality
- Self-representations of the Möbius group
- Some properties of Gaussian reproducing kernel Hilbert spaces and their implications for function approximation and learning theory
- Support Vector Machines
- Theory of Reproducing Kernels
- Universal kernels
- Universality, Characteristic Kernels and RKHS Embedding of Measures
- VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES AND UNIVERSALITY
Cited in
(15)- An approach to the Gaussian RBF kernels via Fock spaces
- Gaussian kernels on nonsimply connected closed Riemannian manifolds are never positive definite
- Characterization theorems for pseudo cross-variograms
- Fractional Gaussian kernels
- A nonparametric test for elliptical distribution based on kernel embedding of probabilities
- Global and local views of the Hilbert space associated to Gaussian kernel
- Generalization of the energy distance by Bernstein functions
- scientific article; zbMATH DE number 1116765 (Why is no real title available?)
- Hilbert space valued Gaussian processes, their kernels, factorizations, and covariance structure
- Gaussian processes with multidimensional distribution inputs via optimal transport and Hilbertian embedding
- The Gaussian kernel on the circle and spaces that admit isometric embeddings of the circle
- Positive definite functions on products of metric spaces by integral transforms
- A Fock space approach to the theory of kernel functions
- Gaussian kernel operators on white noise functional spaces
- Generalization of the HSIC and distance covariance using PDI kernels
This page was built for publication: On Gaussian kernels on Hilbert spaces and kernels on hyperbolic spaces
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2139169)
