English

Stability of Multi-Task Kernel Regression Algorithms

Machine Learning 2013-06-18 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1306.3905,
  title  = {Stability of Multi-Task Kernel Regression Algorithms},
  author = {Julien Audiffren and Hachem Kadri},
  journal= {arXiv preprint arXiv:1306.3905},
  year   = {2013}
}
R2 v1 2026-06-22T00:35:05.085Z