图 书 馆
在线学习算法的错误界限和风险界限Mistake bounds and risk bounds for on-line learning algorithms |
|
| 课程网址: | http://videolectures.net/mcslw04_bianchi_mbrbl/ |
| 主讲教师: | Nicolò Cesa-Bianchi |
| 开课单位: | 米兰大学 |
| 开课时间: | 2007-02-25 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | In statistical learning theory, risk bounds are typically obtained via the manipulation of suprema of empirical processes measuring the largest deviation of the empirical risk from the true risk in a class of models. In this talk we describe the alternative approach of deriving risk bounds for the ensemble of hypotheses obtained by running an arbitrary learning algorithm in an-on line fashion. This allows us to replace the uniform large deviation argument with a simpler argument based on the analysis of the empirical process engendered by the on-line learner. The large deviations of such empirical processes are easily controlled by a single application of Bernstein's inequality for martingales, and the resulting risk bounds exhibit strong data-dependence. |
| 关 键 词: | 风险界限; 数据依赖性; 在线方式运行任意学习算法 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-05-16：cjy |
| 阅读次数: | 97 |