A General Dimension for Approximately Learning Boolean Functions (2002)
| Venue: | IN ALGORITHMIC LEARNING THEORY, 13TH INTERNATIONAL CONFERENCE, ALT 2002 |
| Citations: | 3 - 2 self |
BibTeX
@INPROCEEDINGS{Köbler02ageneral,
author = {Johannes Köbler and Wolfgang Lindner},
title = {A General Dimension for Approximately Learning Boolean Functions},
booktitle = {IN ALGORITHMIC LEARNING THEORY, 13TH INTERNATIONAL CONFERENCE, ALT 2002},
year = {2002},
pages = {139--148},
publisher = {Springer}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We extend the notion of general dimension, a combinatorial characterization of learning complexity for arbitrary query protocols, to encompass approximate learning. This immediately yields a characterization of the learning complexity in the statistical query model. As a further application, we consider approximate learning of DNF formulas and we derive close upper and lower bounds on the number of statistical queries needed. In particular, we show that with respect to the uniform distribution, and for any constant error parameter " < 1=2, the number of statistical queries needed to approximately learn DNF formulas (over n variables and s terms) with tolerance = (1=s) is n .
