The Learning Rate of l2-Coefficient Regularized Classification with Strong Loss
- 点击量:
- 作者：Bao
- 所属单位：数理与信息工程学院
- 文献类型：期刊
- 发表时间：2013-01-01
- 发表刊物：数学学报(英文版)
- 卷号：第29卷
- 期号：第12期
- 页面范围：2397-2408
- Issn号：1439-8516
- 是否译文：否
- 关键字：学习率；分类；亏损；正则；功能空间；数据依赖；正规化；内核
- 摘要：In the present paper, we give an investigation on the learning rate of l2-coefficient regularized classification with strong loss and the data dependent kernel functional spaces. The results show that the learning rate is influenced by the strong convexit
推荐此文
