首页数学
   首页社会学
   首页统计学
0


竞争策略

Competing With Strategies
课程网址: http://videolectures.net/colt2013_sridharan_strategies/  
主讲教师: Karthik Sridharan
开课单位: 康奈尔大学
开课时间: 2013-08-09
课程语种: 英语
中文简介:
我们研究了在线学习的问题,并在一系列策略中定义了遗憾的概念。我们开发了用于分析极小极大速率和在这种情况下导出遗憾最小化算法的工具。虽然最小化通常遗憾概念的标准方法失败了,但通过我们的分析,我们证明了遗传最小化方法的存在,这些方法与以下策略集合竞争:自回归算法,基于统计模型的策略,正则化最小二乘法,并遵循正则化的领导者策略。在某些情况下,我们还可以获得有效的学习算法。
课程简介: We study the problem of online learning with a notion of regret defined with respect to a set of strategies. We develop tools for analyzing the minimax rates and for deriving regret-minimization algorithms in this scenario. While the standard methods for minimizing the usual notion of regret fail, through our analysis we demonstrate existence of regret-minimization methods that compete with such sets of strategies as: autoregressive algorithms, strategies based on statistical models, regularized least squares, and follow the regularized leader strategies. In several cases we also derive efficient learning algorithms.
关 键 词: 在线学习; 遗传最小化; 正则化
课程来源: 视频讲座网
最后编审: 2019-03-13:chenxin
阅读次数: 72