期刊
ANNALS OF STATISTICS
卷 38, 期 1, 页码 526-565出版社
INST MATHEMATICAL STATISTICS-IMS
DOI: 10.1214/09-AOS728
关键词
Regression; reproducing kernel Hilbert space; regulation; least-squares; model selection
资金
- Australian Research Council [DP0559465]
- Israel Science Foundation [666/06]
- Australian Research Council [DP0559465] Funding Source: Australian Research Council
Under mild assumptions on the kernel, we obtain the best known error rates in a regularized learning scenario taking place in the corresponding reproducing kernel Hilbert space (RKHS). The main novelty in the analysis is a proof that one can use a regularization term that grows significantly slower than the standard quadratic growth in the RKHS norm.
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