This paper presents a RKHS, in general, of vector-valued functions intended to be used as hypothesis space for multi-task classification. It extends similar hypothesis spaces that have previously considered in the literature. Assuming this space, an improved Empirical Rademacher Complexity-based generalization bound is derived. The analysis is itself extended to an MKL setting. The connection between the proposed hypothesis space and a Group-Lasso type regularizer is discussed. Finally, experimental results, with some SVM-based Multi-Task Learning problems, underline the quality of the derived bounds and validate the paper's analysis.
Cite
@article{arxiv.1312.2606,
title = {Multi-Task Classification Hypothesis Space with Improved Generalization Bounds},
author = {Cong Li and Michael Georgiopoulos and Georgios C. Anagnostopoulos},
journal= {arXiv preprint arXiv:1312.2606},
year = {2013}
}
Comments
18 pages, 4 figures, submitted to IEEE Transactions on Neural Networks and Learning Systems