Learning rates of regularized regression on the unit sphere

查看全文 作　　者：CAO [1]FeiLong;LIN [2]ShaoBo;CHANG [2]XiangYu;XU [2]ZongBen

机构地区：[1]Institute of Metrology and Computational Science,China Jiliang University;[2]Institute for Information and System Sciences,Xi'an Jiaotong University

出　　处：《Science China Mathematics》索引2013年第56卷第4期,共16页

基　　金：supported by National Natural Science Foundation of China (Grant Nos. 61272023 and 61075054) 摘　　要：This paper addresses the learning algorithm on the unit sphere.The main purpose is to present an error analysis for regression generated by regularized least square algorithms with spherical harmonics kernel.The excess error can be estimated by the sum of sample errors and regularization errors.Our study shows that by introducing a suitable spherical harmonics kernel,the regularization parameter can decrease arbitrarily fast with the sample size. 关键词：单位球面学习算法回归分析正规化最小二乘算法内核样本估计

相关文献

参考文献（25）
引证文献（2）
耦合文献（0）

参考文献(25)

引证文献(2)

互联网出版许可证新出网证(渝)字10号全国400电话 - 免长途话费

Learning rates of regularized regression on the unit sphere

参考文献(25)

引证文献(2)

用户提示