关于严格正函数的拟牛顿方法的有效性][Efficiency of Quasi-Newton Methods on Strictly Positive Functions]

关于严格正函数的拟牛顿方法的有效性 Efficiency of Quasi-Newton Methods on Strictly Positive Functions


课程网址:	http://videolectures.net/nipsworkshops2010_nesterov_eqn/
主讲教师:	Yurii Nesterov
开课单位:	卢旺天主教大学
开课时间:	2011-01-13
课程语种:	英语
中文简介:	在本文中，我们考虑了一类新的凸优化问题，它允许更快的黑箱优化方案。为了分析它们的收敛速度，我们引入了近似解的混合精度的概念，这是绝对精度和相对精度的方便推广。我们证明，对于我们的问题类，自然拟牛顿法总是比标准梯度法更快。同时，经过适当的归一化，我们的结果可以推广到一般的凸无约束最小化问题。
课程简介:	In this talk we consider a new class of convex optimization problems, which admit faster black-box optimization schemes. For analyzing their rate of convergence, we introduce a notion of mixed accuracy of an approximate solution, which is a convenient generalization of the absolute and relative accuracies. We show that for our problem class, a natural Quasi-Newton method is always faster than the standard gradient method. At the same time, after an appropriate normalization, our results can be extended onto the general convex unconstrained minimization problems.
关键词:	黑箱优化; 混合精度; 计算机科学
课程来源:	视频讲座网
数据采集:	2022-12-21：chenjy
最后编审:	2023-05-11：chenjy
阅读次数:	45

境外开放课程导航