Entangled Kernels - Archive ouverte HAL
Communication Dans Un Congrès Année : 2019

Entangled Kernels

Résumé

We consider the problem of operator-valued kernel learning and investigate the possibility of going beyond the well-known separable kernels. Borrowing tools and concepts from the field of quantum computing , such as partial trace and entanglement, we propose a new view on operator-valued kernels and define a general family of kernels that encompasses previously known operator-valued kernels, including separable and transformable kernels. Within this framework, we introduce another novel class of operator-valued kernels called entangled kernels that are not separable. We propose an efficient two-step algorithm for this framework, where the entangled kernel is learned based on a novel extension of kernel alignment to operator-valued kernels. The utility of the algorithm is illustrated on both artificial and real data.
Fichier principal
Vignette du fichier
main.pdf (309.71 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02187162 , version 1 (17-07-2019)

Identifiants

Citer

Riikka Huusari, Hachem Kadri. Entangled Kernels. International Joint Conference of Artificial Intelligence, Aug 2019, Macao, China. pp.2578-2584, ⟨10.24963/ijcai.2019/358⟩. ⟨hal-02187162⟩
105 Consultations
166 Téléchargements

Altmetric

Partager

More