arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.04248math.OC
收藏

非凸光滑复合最优化问题的平均曲率加速复合梯度法

An Average Curvature Accelerated Composite Gradient Method for Nonconvex Smooth Composite Optimization Problems

Jiaming Liang, Renato D. C. Monteiro

摘要:

本文提出了一种求解非凸光滑复合极小化问题的加速复合梯度(ACG)方法,简称AC-ACG方法。与基于已知Lipschitz梯度常数或最大观测曲率序列的众所周知的ACG变体相反,当前的ACG变体基于所有过去观测曲率的平均值。更具体地说,AC-ACG使用直到上一次迭代为止的所有观测到的曲率的平均值的正倍数作为估计当前点处的“函数曲率”的方式,然后使用两个预解式评估来计算下一个曲率。与其他变量Lipschitz估计变体相比,例如,基于最大曲率的那些,AC-ACG总是接受前述的误差,而不管Lipschitz估计结果有多差。最后,计算结果表明,AC-ACG的效率随机生成和现实世界的问题实例。

英文摘要:

This paper presents an accelerated composite gradient (ACG) variant, referred to as the AC-ACG method, for solving nonconvex smooth composite minimization problems. As opposed to well-known ACG variants that are either based on a known Lipschitz gradient constant or a sequence of maximum observed curvatures, the current one is based on the average of all past observed curvatures. More specifically, AC-ACG uses a positive multiple of the average of all observed curvatures until the previous iteration as a way to estimate the "function curvature" at the current point and then two resolvent evaluations to compute the next iterate. In contrast to other variable Lipschitz estimation variants, e.g., the ones based on the maximum curvature, AC-ACG always accepts the aforementioned iterate regardless how poor the Lipschitz estimation turns out to be. Finally, computational results are presented to illustrate the efficiency of AC-ACG on both randomly generated and real-world problem instances.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑