0


正则化路径和坐标下降

Regularization Paths and Coordinate Descent
课程网址: http://videolectures.net/kdd08_hastie_rpcd/  
主讲教师: Trevor Hastie
开课单位: 斯坦福大学
开课时间: 2008-09-26
课程语种: 英语
中文简介:
在面对数据爆炸的统计世界中,正则化已经成为一个重要的组成部分。在许多问题中,我们拥有的变量比观测值要多得多,而套索惩罚及其混合方法已经变得越来越有用。本讲座介绍了一些基于坐标下降的有效算法,用于拟合各种问题的大规模正则化路径。与罗伯·蒂布希拉尼和杰罗姆·弗里德曼合作
课程简介: In a statistical world faced with an explosion of data, regularization has become an important ingredient. In many problems, we have many more variables than observations, and the lasso penalty and its hybrids have become increasingly useful. This talk presents some effective algorithms based on coordinate descent for fitting large scale regularization paths for a variety of problems. Joint work with Rob Tibshirani and Jerome Friedman
关 键 词: 数据爆炸; 统计世界; 坐标下降
课程来源: 视频讲座网
数据采集: 2023-04-16:chenxin01
最后编审: 2023-05-21:chenxin01
阅读次数: 14