arXiv:2206.07588 [stat.ML]AbstractReferencesReviewsResources
Characteristic kernels on Hilbert spaces, Banach spaces, and on sets of measures
Johanna Ziegel, David Ginsbourger, Lutz Dümbgen
Published 2022-06-15Version 1
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.
Related articles: Most relevant | Search more
arXiv:2202.08567 [stat.ML] (Published 2022-02-17)
Robust SVM Optimization in Banach spaces
Positive Definite Kernels in Machine Learning
arXiv:1003.0887 [stat.ML] (Published 2010-03-03)
Universality, Characteristic Kernels and RKHS Embedding of Measures