图 书 馆
Bandit子集选择中的信息复杂性Information Complexity in Bandit Subset Selection |
|
| 课程网址: | http://videolectures.net/colt2013_kaufmann_information/ |
| 主讲教师: | Emilie Kaufmann |
| 开课单位: | 国立高等电信学校 |
| 开课时间: | 2013-08-09 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We consider the problem of efficiently exploring the arms of a stochastic bandit to identify the best subset. Under the PAC and the fixed-budget formulations, we derive improved bounds by using KL-divergence-based confidence intervals. Whereas the application of a similar idea in the regret setting has yielded bounds in terms of the KL-divergence between the arms, our bounds in the pure-exploration setting involve the Chernoff information between the arms. In addition to introducing this novel quantity to the bandits literature, we contribute a comparison between the “racing” and “smart sampling” strategies for pure-exploration problems, finding strong evidence in favor of the latter. |
| 关 键 词: | 有效搜索; 最优子集; 竞速策略; 智能抽样 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-10-17：cwx |
| 阅读次数: | 63 |