拟牛顿近端劈裂法A quasi-Newton proximal splitting method |
|
课程网址: | http://videolectures.net/machine_fadili_splitting_method/ |
主讲教师: | Jalal Fadili |
开课单位: | 卡昂·巴斯·诺曼底大学 |
开课时间: | 2013-01-14 |
课程语种: | 英语 |
中文简介: | 我们描述了有用的一类函数的邻近计算的有效实现;这些实现利用了双重问题的分段线性特性。本文的第二部分将先前的结果应用于凸最小化问题的加速,并导致优雅的拟牛顿方法。优化方法优于现有技术的替代方案。该算法具有广泛的应用,包括信号处理,稀疏回归和恢复,以及机器学习和分类。 |
课程简介: | We describe efficient implementations of the proximity calculation for a useful class of functions; the implementations exploit the piece-wise linear nature of the dual problem. The second part of the paper applies the previous result to acceleration of convex minimization problems, and leads to an elegant quasi-Newton method. The optimization method compares favorably against state-of-the-art alternatives. The algorithm has extensive applications including signal processing, sparse regression and recovery, and machine learning and classification. |
关 键 词: | 计算功能; 拟牛顿法; 信号处理 |
课程来源: | 视频讲座网 |
最后编审: | 2020-05-21:王淑红(课程编辑志愿者) |
阅读次数: | 143 |