在线子模块设置封面,排名和重复的主动学习Online Submodular Set Cover, Ranking, and Repeated Active Learning |
|
课程网址: | http://videolectures.net/nips2011_bilmes_repeated/ |
主讲教师: | Bilmes Jeff A |
开课单位: | 华盛顿大学 |
开课时间: | 2012-09-06 |
课程语种: | 英语 |
中文简介: | 我们提出一个在线预测版本的子模集覆盖与排名和重复主动学习的联系。在每一轮中,学习算法选择一个项目序列。然后,该算法接收一个单调的子模函数,并遭受等于该函数覆盖时间的损失:当按照所选序列选择项时,为实现覆盖约束所需的项数。我们开发了一种在线学习算法,其损失收敛到事后最佳序列的损失。我们提出的算法可以很容易地扩展到每一轮都显示多个函数的设置,以及Bandit和上下文Bandit设置。 |
课程简介: | We propose an online prediction version of submodular set cover with connections to ranking and repeated active learning. In each round, the learning algorithm chooses a sequence of items. The algorithm then receives a monotone submodular function and suffers loss equal to the cover time of the function: the number of items needed, when items are selected in order of the chosen sequence, to achieve a coverage constraint. We develop an online learning algorithm whose loss converges to approximately that of the best sequence in hindsight. Our proposed algorithm is readily extended to a setting where multiple functions are revealed at each round and to bandit and contextual bandit settings. |
关 键 词: | 在线预测版模; 重复的主动学习; 子模函数; 损失收敛 |
课程来源: | 视频讲座网 |
最后编审: | 2020-05-30:张荧(课程编辑志愿者) |
阅读次数: | 45 |