文献类型：期刊文献

英文题名：The Learning Rates of Regularized Regression Based on Reproducing Kernel Banach Spaces

作者：Sheng, Baohuai[1];Ye, Peixin[2,3]

机构：[1]Shaoxing Univ, Dept Math, Shaoxing 312000, Peoples R China;[2]Nankai Univ, Sch Math, Tianjin 300071, Peoples R China;[3]Nankai Univ, LPMC, Tianjin 300071, Peoples R China

年份：2013

卷号：2013

外文期刊名：ABSTRACT AND APPLIED ANALYSIS

收录：SCI-EXPANDED(收录号：WOS:000329719500001)、、Scopus(收录号：2-s2.0-84897814595)、WOS

基金：This work was supported partially by the National Natural Science Foundation of China under Grant nos. 10871226, 61179041, 11271199. The authors thank the reviewers for giving many valuable suggestions and comments which make the paper presented in a better form.

语种：英文

外文摘要：We study the convergence behavior of regularized regression based on reproducing kernel Banach spaces (RKBSs). The convex inequality of uniform convex Banach spaces is used to show the robustness of the optimal solution with respect to the distributions. The learning rates are derived in terms of the covering number and K-functional.