Generalization bounds for averaged classifiers

Details Generalization bounds for averaged classifiers Generalization bounds for averaged classifiers

2004-10-05

arxiv.org/abs/math/0410092v1

Annals of Statistics 2004, Vol. 32, No. 4, 1698-1722

Mathematics

Statistics Theory

Published by the Institute of Mathematical Statistics (http://www.imstat.org) in the Annals of Statistics (http://www.imstat

Scientific paper

10.1214/009053604000000058

We study a simple learning algorithm for binary classification. Instead of predicting with the best hypothesis in the hypothesis class, that is, the hypothesis that minimizes the training error, our algorithm predicts with a weighted average of all hypotheses, weighted exponentially with respect to their training error. We show that the prediction of this algorithm is much more stable than the prediction of an algorithm that predicts with the best hypothesis. By allowing the algorithm to abstain from predicting on some examples, we show that the predictions it makes when it does not abstain are very reliable. Finally, we show that the probability that the algorithm abstains is comparable to the generalization error of the best hypothesis in the class.

Affiliated with

Also associated with

No associations

Rating

Generalization bounds for averaged classifiers does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Generalization bounds for averaged classifiers, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Generalization bounds for averaged classifiers will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-103233