Operator-valued positive definite kernels and differentiable universality
From MaRDI portal
Abstract: We present a characterization for a positive definite operator valued kernel to be universal or -universal, and apply these characterizations to a family of operator valued kernels that are shown to be well behaved. Later, we obtain a characterization for an operator valued differentiable kernel to be -universal and -universal. In order to obtain such characterization and examples we generalize some well known results concerning the structure of differentiable kernels to the operator valued context. On the examples is given an emphasis on the radial kernels on Euclidean spaces.
Recommendations
- Universality, Characteristic Kernels and RKHS Embedding of Measures
- scientific article; zbMATH DE number 7526382
- Universalities of reproducing kernels revisited
- VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES AND UNIVERSALITY
- Function spaces for conditionally positive definite operator-valued kernels
Cites work
- A general bilinear vector integral
- A unifying framework in vector-valued reproducing kernel Hilbert spaces for manifold regularization and co-regularized multi-view learning
- Approximation by translates of a positive definite function
- Conditionally positive definite matrix valued kernels on Euclidean spaces
- Derivative reproducing properties for kernel methods in learning theory
- Dimension walks and Schoenberg spectral measures
- Hilbert space embeddings and metrics on probability measures
- scientific article; zbMATH DE number 5968915 (Why is no real title available?)
- scientific article; zbMATH DE number 3875591 (Why is no real title available?)
- scientific article; zbMATH DE number 3576139 (Why is no real title available?)
- scientific article; zbMATH DE number 1466451 (Why is no real title available?)
- Kernel distribution embeddings: universal kernels, characteristic kernels and kernel metrics on distributions
- Learning Theory
- Manifolds, tensor analysis, and applications.
- Matrix-valued kernels for shape deformation analysis
- On the derivatives of radial positive definite functions
- On the mathematical foundations of learning
- Operator-valued positive definite kernels on tubes
- Refinement of Operator-valued Reproducing Kernels
- Scattered Data Approximation
- Sous-espaces d'espaces vectoriels topologiques et noyaux associés. (Noyaux reproduisants.)
- Strictly positive definite functions in \(\mathbb R^{d}\)
- Strictly positive definite multivariate covariance functions on spheres
- Theory of Reproducing Kernels
- Universality, Characteristic Kernels and RKHS Embedding of Measures
- VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES AND UNIVERSALITY
Cited in
(8)- On Gaussian kernels on Hilbert spaces and kernels on hyperbolic spaces
- Generalized Whittle-Matérn and polyharmonic kernels
- Universalities of reproducing kernels revisited
- scientific article; zbMATH DE number 7526382 (Why is no real title available?)
- Learning with centered reproducing kernels
- Operator-valued Gaussian processes and their covariance kernels
- From classical to quantum: polymorphisms in non-commutative probability
- Operator-valued kernels, machine learning, and dynamical systems
This page was built for publication: Operator-valued positive definite kernels and differentiable universality
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5083439)
