期刊
ANALYSIS AND APPLICATIONS
卷 8, 期 2, 页码 161-183出版社
WORLD SCIENTIFIC PUBL CO PTE LTD
DOI: 10.1142/S0219530510001564
关键词
Learning theory; statistical adaptation; regression; error bounds
资金
- City University of Hong Kong [7200111(MA), 7002492 (MA)]
- NSF [0325113]
- Division of Computing and Communication Foundations
- Direct For Computer & Info Scie & Enginr [0325113] Funding Source: National Science Foundation
We consider learning algorithms induced by regularization methods in the regression setting. We show that previously obtained error bounds for these algorithms, using a priori choices of the regularization parameter, can be attained using a suitable a posteriori choice based on cross-validation. In particular, these results prove adaptation of the rate of convergence of the estimators to the minimax rate induced by the effective dimension of the problem. We also show universal consistency for this broad class of methods which includes regularized least-squares, truncated SVD, Landweber iteration and nu-method.
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