Support vector machines regression with -regularizer

详细信息    查看全文

• 作者：Hongzhi Tong ; Di-Rong Chen ; Fenghong Yang
• 关键词：Support vector machines regression ; Coefficient regularization ; Learning rate ; Reproducing kernel Hilbert spaces ; Error decomposition
• 刊名：Journal of Approximation Theory
• 出版年：2012
• 出版时间：October, 2012
• 年：2012
• 卷：164
• 期：10
• 页码：1331-1344
• 全文大小：226 K

文摘

The classical support vector machines regression (SVMR) is known as a regularized learning algorithm in reproducing kernel Hilbert spaces (RKHS) with a -insensitive loss function and an RKHS norm regularizer. In this paper, we study a new SVMR algorithm where the regularization term is proportional to -norm of the coefficients in the kernel ensembles. We provide an error analysis of this algorithm, an explicit learning rate is then derived under some assumptions.