期刊
ANALYSIS AND APPLICATIONS
卷 9, 期 4, 页码 369-382出版社
WORLD SCIENTIFIC PUBL CO PTE LTD
DOI: 10.1142/S0219530511001893
关键词
Learning theory; error bounds; regression
资金
- City University of Hong Kong [9041525, 7002492]
We consider a wide class of error bounds developed in the context of statistical learning theory which are expressed in terms of functionals of the regression function, for instance, its norm in a reproducing kernel Hilbert space or other functional space. These bounds are unstable in the sense that a small perturbation of the regression function can induce an arbitrary large increase of the relevant functional and make the error bound useless. Using a known result involving Fano inequality, we show how stability can be recovered.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据