图 书 馆
组合半强盗的一阶遗憾界First-order regret bounds for combinatorial semi-bandits |
|
| 课程网址: | https://videolectures.net/videos/colt2015_neu_online_learning |
| 主讲教师: | Gergely Neu |
| 开课单位: | 信息不详。欢迎您在右侧留言补充。 |
| 开课时间: | 2025-02-04 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We consider the problem of online combinatorial optimization under semi-bandit feedback, where a learner has to repeatedly pick actions from a combinatorial decision set in order to minimize the total losses associated with its decisions. After making each decision, the learner observes the losses associated with its action, but not other losses. The performance of the learner is measured in terms of its total expected regret against the best fixed action after $T$ rounds. In this paper, we propose a computationally efficient algorithm that improves existing worst-case guarantees of $O(\sqrt{T})$ to $O(\sqrt{L_T^*})$, where $L_T^*$ is the total loss of the best action. Our algorithm is among the first to achieve such guarantees in a partial-feedback scheme, and the first one to do so in a combinatorial setting. |
| 关 键 词: | 组合优化问题：总损失; 组合决策 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2025-03-30：zsp |
| 最后编审: | 2025-03-31：liyy |
| 阅读次数: | 3 |