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

Autor:	Ziegel, Johanna, Ginsbourger, David, Dümbgen, Lutz
Rok vydání:	2022
Předmět:	Statistics - Machine Learning Computer Science - Machine Learning Mathematics - Functional Analysis Mathematics - Statistics Theory
Druh dokumentu:	Working Paper
Popis:	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.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2206.07588 Zobrazit plný text záznamu View this record from Arxiv