Generalization bounds for averaged classifiers

@inproceedings{Freund2004GeneralizationBF,
  title={Generalization bounds for averaged classifiers},
  author={Yoav Freund and Yishay Mansour and Robert E. Schapire},
  year={2004}
}
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… CONTINUE READING

From This Paper

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 48 CITATIONS

Similar Papers

Loading similar papers…