Invariant kernels on the space of complex covariance matrices - Optimization and learning for Data Science Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Invariant kernels on the space of complex covariance matrices

Salem Said

Résumé

The present work develops certain analytical tools required to construct and compute invariant kernels on the space of complex covariance matrices. The main result is the $\mathrm{L}^1\,-$Godement theorem, which states that any invariant kernel, which is (in a certain natural sense) also integrable, can be computed by taking the inverse spherical transform of a positive function. General expressions for inverse spherical transforms are then provided, which can be used to explore new families of invariant kernels, at a rather moderate computational cost. A further, alternative approach for constructing new invariant kernels is also introduced, based on Ramanujan's master theorem for symmetric cones.
Fichier principal
Vignette du fichier
Kernels_Complex_Cov.pdf (286.97 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04525081 , version 1 (28-03-2024)
hal-04525081 , version 2 (25-07-2024)

Identifiants

  • HAL Id : hal-04525081 , version 2

Citer

Cyrus Mostajeran, Salem Said. Invariant kernels on the space of complex covariance matrices. 2024. ⟨hal-04525081v2⟩
20 Consultations
14 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More