图 书 馆
非光滑凸优化问题的拟牛顿法A Quasi-Newton Approach to Nonsmooth Convex Optimization |
|
| 课程网址: | http://videolectures.net/icml08_yu_aqna/ |
| 主讲教师: | Jin Yu |
| 开课单位: | 澳大利亚ICT卓越研究中心 |
| 开课时间: | 2008-08-29 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We extend the well-known BFGS quasi-Newton method and its limited-memory variant (LBFGS) to the optimization of nonsmooth convex objectives. This is done in a rigorous fashion by generalizing three components of BFGS to subdifferentials: The local quadratic model, the identification of a descent direction, and the Wolfe line search conditions. We apply the resulting sub(L)BFGS algorithm to L2-regularized risk minimization with binary hinge loss, and its direction-finding component to L1-regularized risk minimization with logistic loss. In both settings our generic algorithms perform comparable to or better than their counterparts in specialized state-of-the-art solvers. |
| 关 键 词: | 拟牛顿方法; 二元铰链; 逻辑损失 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2022-11-02：chenjy |
| 最后编审: | 2022-11-02：chenjy |
| 阅读次数: | 46 |