Sciweavers

Share
COLT
2000
Springer

PAC Analogues of Perceptron and Winnow via Boosting the Margin

9 years 6 months ago
PAC Analogues of Perceptron and Winnow via Boosting the Margin
We describe a novel family of PAC model algorithms for learning linear threshold functions. The new algorithms work by boosting a simple weak learner and exhibit complexity bounds remarkably similar to those of known online algorithms such as Perceptron and Winnow, thus suggesting that these well-studied online algorithms in some sense correspond to instances of boosting. We show that the new algorithms can be viewed as natural PAC analogues of the online ¡ -norm algorithms which have recently been studied by Grove, Littlestone, and Schuurmans [16] and Gentile and Littlestone [15]. As special cases of the algorithm, by taking ¡£¢¥¤ and ¡£¢¥¦ we obtain natural boostingbased PAC analogues of Perceptron and Winnow respectively. The ¡§¢¨¦ case of our algorithm can also be viewed as a generalization (with an improved sample complexity bound) of Jackson and Craven’s PAC-model boosting-based algorithm for learning “sparse perceptrons” [20]. The analysis of the generaliz...
Rocco A. Servedio
Added 02 Aug 2010
Updated 02 Aug 2010
Type Conference
Year 2000
Where COLT
Authors Rocco A. Servedio
Comments (0)
books