Stability and generalization
Stability and generalization
复制标题
DOI：
10.1162/153244302760200704
复制
发表时间：
2002-06-01
影响因子：
6
通讯作者：
Elisseeff, A
中科院分区：
文献类型：
--
作者：
Bousquet, O;Elisseeff, A
我们定义了学习算法的稳定性概念，并展示了如何使用这些概念来基于经验误差和遗漏误差导出泛化误差界。我们使用的方法可以应用在回归框架中，也可以应用于分类框架中，当分类器是通过对实值函数进行阈值处理获得的时候。我们研究了一大类学习算法的稳定性，如基于正则化的算法。特别地，我们重点研究了Hilbert空间正则化和Kullback-Leibler正则化。我们演示了如何将结果应用于支持向量机进行回归和分类。
We define notions of stability for learning algorithms and show how to use these notions to derive generalization error bounds based on the empirical error and the leave-one-out error. The methods we use can be applied in the regression framework as well as in the classification one when the classifier is obtained by thresholding a real-valued function. We study the stability properties of large classes of learning algorithms such as regularization based algorithms. In particular we focus on Hilbert space regularization and Kullback-Leibler regularization. We demonstrate how to apply the results to SVM for regression and classification.