A Fock space approach to the theory of strictly positive kernels

08/05/2022

∙

In this paper, we give a new approach to the theory of strictly positive kernels. Our method is based on the structure of Fock spaces. As its applications, various examples of strictly positive kernels are given. Moreover, we give a new proof of the universal approximation theorem for the Gauss kernel.

READ FULL TEXT

A Fock space approach to the theory of strictly positive kernels

Positive Definite Multi-Kernels for Scattered Data Interpolations

Hidden Positivity and a New Approach to Numerical Computation of Hausdorff Dimension: Higher Order Methods

Optimal measures and Markov transition kernels

Borel Kernels and their Approximation, Categorically

Strictly proper kernel scores and characteristic kernels on compact spaces

Kernels over Sets of Finite Sets using RKHS Embeddings, with Application to Bayesian (Combinatorial) Optimization

Strict positive definiteness of convolutional and axially symmetric kernels on d-dimensional spheres

A Fock space approach to the theory of strictly positive kernels

Related Research

Positive Definite Multi-Kernels for Scattered Data Interpolations

Hidden Positivity and a New Approach to Numerical Computation of Hausdorff Dimension: Higher Order Methods

Optimal measures and Markov transition kernels

Borel Kernels and their Approximation, Categorically

Strictly proper kernel scores and characteristic kernels on compact spaces

Kernels over Sets of Finite Sets using RKHS Embeddings, with Application to Bayesian (Combinatorial) Optimization

Strict positive definiteness of convolutional and axially symmetric kernels on d-dimensional spheres