Online Learning of Maximum P-Norm Margin Classifiers with Bias
Abstract
We propose a new online learning algorithm which provably approximates maximum margin classifiers with bias, where the margin is defined in terms of p-norm distance. Although learning of linear classifiers with bias can be reduced to learning of those without bias, the known reduction might lose the margin and slow down the convergence of online learning algorithms. Our algorithm, unlike previous online learning algorithms, implicitly uses a new reduction which preserves the margin and avoids such possible deficiencies. Our preliminary experiments show that our algorithm runs much faster than previous algorithms especially when the underlying linear classifier has large bias.
Cite
Text
Ishibashi et al. "Online Learning of Maximum P-Norm Margin Classifiers with Bias." Annual Conference on Computational Learning Theory, 2008.Markdown
[Ishibashi et al. "Online Learning of Maximum P-Norm Margin Classifiers with Bias." Annual Conference on Computational Learning Theory, 2008.](https://mlanthology.org/colt/2008/ishibashi2008colt-online/)BibTeX
@inproceedings{ishibashi2008colt-online,
title = {{Online Learning of Maximum P-Norm Margin Classifiers with Bias}},
author = {Ishibashi, Kosuke and Hatano, Kohei and Takeda, Masayuki},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2008},
pages = {69-80},
url = {https://mlanthology.org/colt/2008/ishibashi2008colt-online/}
}