Leave-One-Out Bounds for Kernel Methods

Leave-One-Out Bounds for Kernel Methods
复制标题

DOI:
10.1162/089976603321780326
复制
发表时间:
2003-06
期刊:
影响因子:
2.9
通讯作者:
Tong Zhang
Tong Zhang
中科院分区:
计算机科学4区
文献类型:
--
作者:
Tong Zhang

文献摘要

被引文献

相似文献

在这篇文章中,我们研究了核方法的留一式交叉验证边界。在我们的分析的基本要素是一个约束的参数估计稳定的正则化核公式。使用这个结果,我们得到预期的留一交叉验证错误的界限,从而导致预期的各种内核算法的泛化界限。此外,我们还得到了留一法误差的方差界。我们将我们的分析应用到一些分类和回归问题,并将它们与以前的结果进行比较。
In this article, we study leave-one-out style cross-validation bounds for kernel methods. The essential element in our analysis is a bound on the parameter estimation stability for regularized kernel formulations. Using this result, we derive bounds on expected leave-one-out cross-validation errors, which lead to expected generalization bounds for various kernel algorithms. In addition, we also obtain variance bounds for leave-oneout errors. We apply our analysis to some classification and regression problems and compare them with previous results.