图 书 馆
马尔可夫样本的鲁棒性和广义性Robustness and Generalizability for Markovian Samples |
|
| 课程网址: | http://videolectures.net/ecmlpkdd09_xu_rgms/ |
| 主讲教师: | Zhao Xu |
| 开课单位: | 慕尼黑大学 |
| 开课时间: | 2009-10-20 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We consider robustness of learning algorithms and prove that under a very general setup, robustness of an algorithm implies that it generalizes, and consequently, a robust algorithm that asymptotically minimizes empirical risk is consistent. In particular, this relationship holds in the case where both training samples and testing samples are generated according to evolving of a Markovian chain satisfying the Doeblin condition. We further provide conditions that ensure robustness and hence generalizability and in some cases consistency, all under the Markovian setup. Two notable examples are support vector machines and Lasso. |
| 关 键 词: | 学习算法; 鲁棒性; 马尔可夫链 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-03-27：lxf |
| 阅读次数: | 64 |