arXivDaily arXiv每日学术速递 周一至周五更新
arXiv math/0410092math.STstat.TH
收藏

平均分类器的推广界

Generalization bounds for averaged classifiers

Yoav Freund, Yishay Mansour, Robert E. Schapire

摘要:

研究了一种简单的二进制分类学习算法。我们的算法不是用假设类中的最佳假设进行预测,也就是说,最小化训练误差的假设,而是用所有假设的加权平均值进行预测,相对于其训练误差呈指数加权。我们表明,该算法的预测是更稳定的预测算法,预测最好的假设。通过允许算法放弃预测的一些例子,我们表明,它的预测时,它不弃权是非常可靠的。最后,我们表明该算法放弃的概率与该类中最佳假设的泛化误差相当。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑