图 书 馆
权衡错误和未知的预测Trading off Mistakes and Don't-Know Predictions |
|
| 课程网址: | http://videolectures.net/nips2010_blum_tom/ |
| 主讲教师: | Avrim Blum |
| 开课单位: | 卡内基梅隆大学 |
| 开课时间: | 2011-03-25 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We discuss an online learning framework in which the agent is allowed to say "I don't know2 as well as making incorrect predictions on given examples. We analyze the trade off between saying "I don't know" and making mistakes. If the number of don't know predictions is forced to be zero, the model reduces to the well-known mistake-bound model introduced by Littlestone [Lit88]. On the other hand, if no mistakes are allowed, the model reduces to KWIK framework introduced by Li et. al. [LLW08]. We propose a general, though inefficient, algorithm for general finite concept classes that minimizes the number of don't-know predictions if a certain number of mistakes are allowed. We then present specific polynomial-time algorithms for the concept classes of monotone disjunctions and linear separators. |
| 关 键 词: | 在线学习; 犯错; 错误约束模型 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-07-25：cwx |
| 阅读次数: | 45 |