The Impact of Unlabeled Patterns in Rademacher Complexity Theory for Kernel Classifiers
Abstract
We derive here new generalization bounds, based on Rademacher Complexity theory, for model selection and error estimation of linear (kernel) classifiers, which exploit the availability of unlabeled samples. In particular, two results are obtained: the first one shows that, using the unlabeled samples, the confidence term of the conventional bound can be reduced by a factor of three; the second one shows that the unlabeled samples can be used to obtain much tighter bounds, by building localized versions of the hypothesis class containing the optimal classifier.
Cite
Text
Oneto et al. "The Impact of Unlabeled Patterns in Rademacher Complexity Theory for Kernel Classifiers." Neural Information Processing Systems, 2011.Markdown
[Oneto et al. "The Impact of Unlabeled Patterns in Rademacher Complexity Theory for Kernel Classifiers." Neural Information Processing Systems, 2011.](https://mlanthology.org/neurips/2011/oneto2011neurips-impact/)BibTeX
@inproceedings{oneto2011neurips-impact,
title = {{The Impact of Unlabeled Patterns in Rademacher Complexity Theory for Kernel Classifiers}},
author = {Oneto, Luca and Anguita, Davide and Ghio, Alessandro and Ridella, Sandro},
booktitle = {Neural Information Processing Systems},
year = {2011},
pages = {585-593},
url = {https://mlanthology.org/neurips/2011/oneto2011neurips-impact/}
}