pith. sign in

arxiv: 1306.3905 · v1 · pith:I2P3QISAnew · submitted 2013-06-17 · 💻 cs.LG · stat.ML

Stability of Multi-Task Kernel Regression Algorithms

classification 💻 cs.LG stat.ML
keywords multi-taskregressionkernelkernelsalgorithmslearningoperator-valuedspaces
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.