Search Results for author: Nathael Da Costa

Found 2 papers, 0 papers with code

Invariant kernels on Riemannian symmetric spaces: a harmonic-analytic approach

no code implementations30 Oct 2023 Nathael Da Costa, Cyrus Mostajeran, Juan-Pablo Ortega, Salem Said

This work aims to prove that the classical Gaussian kernel, when defined on a non-Euclidean symmetric space, is never positive-definite for any choice of parameter.

Geometric Learning with Positively Decomposable Kernels

no code implementations20 Oct 2023 Nathael Da Costa, Cyrus Mostajeran, Juan-Pablo Ortega, Salem Said

Classical kernel methods are based on positive-definite kernels, which map data spaces into reproducing kernel Hilbert spaces (RKHS).

Cannot find the paper you are looking for? You can Submit a new open access paper.