A Note on Extending Generalization Bounds for Binary Large-Margin Classifiers to Multiple Classes
Abstract
A generic way to extend generalization bounds for binary large-margin classifiers to large-margin multi-category classifiers is presented. The simple proceeding leads to surprisingly tight bounds showing the same $\tilde{O}(d^2)$ scaling in the number d of classes as state-of-the-art results. The approach is exemplified by extending a textbook bound based on Rademacher complexity, which leads to a multi-class bound depending on the sum of the margin violations of the classifier.
Cite
Text
Dogan et al. "A Note on Extending Generalization Bounds for Binary Large-Margin Classifiers to Multiple Classes." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2012. doi:10.1007/978-3-642-33460-3_13Markdown
[Dogan et al. "A Note on Extending Generalization Bounds for Binary Large-Margin Classifiers to Multiple Classes." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2012.](https://mlanthology.org/ecmlpkdd/2012/dogan2012ecmlpkdd-note/) doi:10.1007/978-3-642-33460-3_13BibTeX
@inproceedings{dogan2012ecmlpkdd-note,
title = {{A Note on Extending Generalization Bounds for Binary Large-Margin Classifiers to Multiple Classes}},
author = {Dogan, Ürün and Glasmachers, Tobias and Igel, Christian},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2012},
pages = {122-129},
doi = {10.1007/978-3-642-33460-3_13},
url = {https://mlanthology.org/ecmlpkdd/2012/dogan2012ecmlpkdd-note/}
}