图 书 馆
用于计算预算模型选择的Oracle不等式Oracle inequalities for computationally budgeted model selection |
|
| 课程网址: | http://videolectures.net/colt2011_agarwal_model/ |
| 主讲教师: | Alekh Agarwal |
| 开课单位: | 微软公司 |
| 开课时间: | 2011-08-02 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We analyze general model selection procedures using penalized empirical loss minimization under computational constraints. While classical model selection approaches do not consider computational aspects of performing model selection, we argue that any practical model selection procedure must not only trade o estimation and approximation error, but also the effects of the computational effort required to compute empirical minimizers for di fferent function classes. We provide a framework for analyzing such problems, and we give algorithms for model selection under a computational budget. These algorithms satisfy oracle inequalities that show that the risk of the selected model is not much worse than if we had devoted all of our computational budget to the best function class. |
| 关 键 词: | 计算约束; 计算预算; oracle不等式 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-04-22：chenxin |
| 阅读次数: | 177 |