机器学习之凸优化理论
文章平均质量分 66
focus_clam
这个作者很懒,什么都没留下…
展开
-
(凸优化理论学习笔记2017/3/18)Theory of Convex Optimeization for Machine Learning(Sebatien Bubeck)
Section5.2: Smooth saddle-point representation of a non-smooth functionQuite often the non-smoothness of a function f comes from a max operation.5.2.1: Saddle point computation计算表达式; 函数需满足条件:紧凑凸集,并且原创 2017-03-18 19:07:46 · 1244 阅读 · 1 评论 -
(凸优化理论学习笔记2017/3/17)Theory of Convex Optimeization for Machine Learning(Sebatien Bubeck)
Chapter 5: Beyond the black-box modelSection5.1: propose a first order method with a 1/t^2 convergence rate, despite the non-smoothnessSection5.2: the function is the maximum of smooth functionsSect原创 2017-03-17 11:08:06 · 719 阅读 · 0 评论