图 书 馆
校准土匪的公平性Calibrated fairness in bandits |
|
| 课程网址: | http://videolectures.net/kdd2017_radanovic_bandits/ |
| 主讲教师: | Goran Radanovic |
| 开课单位: | 哈佛大学工程与应用科学学院 |
| 开课时间: | 2017-12-01 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We study fairness within the stochastic, multi-armed bandit (MAB) decision making framework. We adapt the fairness framework of “treating similar individuals similarly” [5] to this setting. Here, an ‘individual’ corresponds to an arm and two arms are ‘similar’ if they have a similar quality distribution. First, we adopt a smoothness constraint that if two arms have a similar quality distribution then the probability of selecting each arm should be similar. In addition, we define the fairness regret, which corresponds to the degree to which an algorithm is not calibrated, where perfect calibration requires that the probability of selecting an arm is equal to the probability with which the arm has the best quality realization. We show that a variation on Thompson sampling satisfies smooth fairness for total variation distance, and give an O˜((kT ) 2/3 ) bound on fairness regret. This complements prior work [12], which protects an on-average better arm from being less favored. We also explain how to extend our algorithm to the dueling bandit settiing. |
| 关 键 词: | 校准公平; 公平框架; 多臂强盗; 质量分布 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2023-04-22：chenxin01 |
| 最后编审: | 2023-05-18：chenxin01 |
| 阅读次数: | 34 |