On the Generalization Ability of On-line Learning Algorithms (2001)
| Venue: | IEEE Transactions on Information Theory |
| Citations: | 83 - 6 self |
BibTeX
@ARTICLE{Cesa-Bianchi01onthe,
author = {Nicolo Cesa-Bianchi and Alex Conconi and Claudio Gentile},
title = {On the Generalization Ability of On-line Learning Algorithms},
journal = {IEEE Transactions on Information Theory},
year = {2001},
volume = {50},
pages = {2050--2057}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
In this paper we show that on-line algorithms for classification and regression can be naturally used to obtain hypotheses with good datadependent tail bounds on their risk. Our results are proven without requiring complicated concentration-of-measure arguments and they hold for arbitrary on-line learning algorithms. Furthermore, when applied to concrete on-line algorithms, our results yield tail bounds that in many cases are comparable or better than the best known bounds.
