Stability of Multi-Task Kernel Regression Algorithms

Julien Audiffren (1) , Hachem Kadri (1)

1 LIF - Laboratoire d'informatique Fondamentale de Marseille

We study the stability properties of nonlinear multi-task regression in reproducing Hilbert spaces with operator-valued kernels. Such kernels, a.k.a. multi-task kernels, are appropriate for learning prob- lems with nonscalar outputs like multi-task learning and structured out- put prediction. We show that multi-task kernel regression algorithms are uniformly stable in the general case of infinite-dimensional output spaces. We then derive under mild assumption on the kernel generaliza- tion bounds of such algorithms, and we show their consistency even with non Hilbert-Schmidt operator-valued kernels . We demonstrate how to apply the results to various multi-task kernel regression methods such as vector-valued SVR and functional ridge regression.

Mots clés: Uniform Stability; Multi-task kernels; Hilbert space valued RKHS; Regression Generalization bounds

Domaines: Apprentissage [cs.LG]

Julien Audiffren, Hachem Kadri. Stability of Multi-Task Kernel Regression Algorithms. 2013. ⟨hal-00834994⟩