arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.07822math.OC
收藏

具有不精确子问题解的梯度采样方法和梯度聚集

Gradient Sampling Methods with Inexact Subproblem Solutions and Gradient Aggregation

Frank E. Curtis, Minhan Li

摘要:

梯度采样(GS)已被证明是一种有效的方法来最小化的目标函数,可能是非凸和/或非光滑的。当代GS方法的计算成本最高的部分是需要在每次迭代中求解凸二次子问题。在本文中,提出了一种策略,允许使用这些子问题的不精确的解决方案,其中,证明了在该文件中,可以被纳入没有损失的理论收敛保证。数值实验表明,利用不精确的子问题的解决方案,可以不断减少所需的GS方法的计算量。此外,提出了一种策略,用于聚合梯度信息后,子问题得到解决(可能不准确),已被利用在捆绑方法非光滑最优化。它被证明是可以引入的聚合计划,而不会失去理论上的收敛保证。数值实验表明,将这种梯度聚合方法大大减少了GS方法所需的计算工作量。

英文摘要:

Gradient sampling (GS) has proved to be an effective methodology for the minimization of objective functions that may be nonconvex and/or nonsmooth. The most computationally expensive component of a contemporary GS method is the need to solve a convex quadratic subproblem in each iteration. In this paper, a strategy is proposed that allows the use of inexact solutions of these subproblems, which, as proved in the paper, can be incorporated without the loss of theoretical convergence guarantees. Numerical experiments show that by exploiting inexact subproblem solutions, one can consistently reduce the computational effort required by a GS method. Additionally, a strategy is proposed for aggregating gradient information after a subproblem is solved (potentially inexactly), as has been exploited in bundle methods for nonsmooth optimization. It is proved that the aggregation scheme can be introduced without the loss of theoretical convergence guarantees. Numerical experiments show that incorporating this gradient aggregation approach substantially reduces the computational effort required by a GS method.

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。

↑