arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.04579math.OC
收藏

在非光滑优化的梯度采样方法中使用二阶信息

Using second-order information in gradient sampling methods for nonsmooth optimization

Bennet Gebken

AI总结:

本文提出基于Goldstein eps-次微分的非光滑函数二阶信息新概念,通过最大化Taylor展开构建模型并设计采样下降方法,证明其在凸或max型目标下的收敛性,数值实验显示超线性行为。

摘要:

本文受Goldstein eps-次微分的启发,引入了一种新的非光滑函数二阶信息概念。该概念包含给定点周围eps-球内所有现有二阶Taylor展开的系数。基于这一概念,我们将目标函数定义为这些Taylor展开的最大值模型,并推导出一种在实际中对其进行近似的采样方案。对该模型进行最小化可导出一个简单的下降方法,我们证明了当目标函数为凸函数或max型函数时该方法的收敛性。虽然我们未证明该方法的任何收敛速率,但数值实验表明,相对于目标函数的oracle调用次数,其表现出超线性行为。

英文摘要:

In this article, we introduce a novel concept for second-order information of a nonsmooth function inspired by the Goldstein eps-subdifferential. It comprises the coefficients of all existing second-order Taylor expansions in an eps-ball around a given point. Based on this concept, we define a model of the objective as the maximum of these Taylor expansions, and derive a sampling scheme for its approximation in practice. Minimization of this model induces a simple descent method, for which we show convergence for the case where the objective is convex or of max-type. While we do not prove any rate of convergence of this method, numerical experiments suggest superlinear behavior with respect to the number of oracle calls of the objective.

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。

↑