图 书 馆
在线学习：排除遗憾Online Learning: Beyond Regret |
|
| 课程网址: | http://videolectures.net/colt2011_sridharan_online/ |
| 主讲教师: | Karthik Sridharan |
| 开课单位: | 康奈尔大学 |
| 开课时间: | 2011-08-02 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We study online learnability of a wide class of problems, extending the results of [21] to general notions of performance measure well beyond external regret. Our framework simultaneously captures such well-known notions as internal and general ϕ-regret, learning with non-additive global cost functions, Blackwell's approachability, calibration of forecasters, and more. We show that learnability in all these situations is due to control of the same three quantities: a martingale convergence term, a term describing the ability to perform well if future is known, and a generalization of sequential Rademacher complexity, studied in [21]. Since we directly study complexity of the problem instead of focusing on efficient algorithms, we are able to improve and extend many known results which have been previously derived via an algorithmic construction. |
| 关 键 词: | 在线学习; 遗憾; 算法 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-02-23：chenxin |
| 阅读次数: | 266 |