图 书 馆
汤普森抽样:一个可证明的强盗问题的良好贝叶斯启发式Thompson Sampling: a provably good Bayesian heuristic for bandit problems |
|
| 课程网址: | http://videolectures.net/lsoldm2013_agrawal_thompson_sampling/ |
| 主讲教师: | Shipra Agrawal |
| 开课单位: | 微软印度研究院 |
| 开课时间: | 2013-11-07 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Multi-armed bandit problem is a basic model for managing the exploration/exploitation trade-off that arises in many situations. Thompson Sampling [Thompson 1933] is one of the earliest heuristic for the multi-armed bandit problem, which has recently seen a surge of interest due to its elegance, flexibility, efficiency, and promising empirical performance. In this talk, I will discuss recent results showing that Thompson Sampling gives near-optimal regret for several popular variants of the multi-armed bandit problem, including linear contextual bandits. Interestingly, these works provide a prior-free frequentist type analysis of a Bayesian heuristic, and thereby a rigorous support for the intuition that once you acquire enough data, it doesn't matter what prior you started from because your posterior will be accurate enough. |
| 关 键 词: | 土匪问题; 基本模型; 多臂强盗 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2023-05-15：chenxin01 |
| 最后编审: | 2023-05-18：chenxin01 |
| 阅读次数: | 38 |