Steppest descent analysis for unregularized linear prediction with strictly convex penaltiesSteppest descent analysis for unregularized linear prediction with strictly convex penalties |
|
课程网址: | http://videolectures.net/nipsworkshops2011_telgarsky_penalties/ |
主讲教师: | Matus Telgarsky |
开课单位: | 加州大学圣地亚哥分校 |
开课时间: | 2012-01-25 |
课程语种: | 英语 |
中文简介: | 该手稿提供了一种收敛性分析,该研究从对非均匀化线性预测的推动研究中得出。在这里,经验风险 - 包括由线性项组成的严格凸罚 - 可能不会强烈凸,甚至达不到最小化。该分析在线演示回归,可分解目标和提升。 |
课程简介: | This manuscript presents a convergence analysis, generalized from a study of boosting, of unregularized linear prediction. Here the empirical risk — incorporating strictly convex penalties composed with a linear term — may fail to be strongly convex, or even attain a minimizer. This analysis is demonstrated on linear regression, decomposable objectives, and boosting. |
关 键 词: | 收敛性分析; 非均匀化线性预测; 回归 |
课程来源: | 视频讲座网 |
最后编审: | 2019-09-07:lxf |
阅读次数: | 35 |