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 2410.01382math.OC
收藏

通过Goldstein子微分分析非光滑优化中的收敛速度及其在下降法中的应用

Analyzing the speed of convergence in nonsmooth optimization via the Goldstein subdifferential with application to descent methods

Technical University of Munich(慕尼黑工业大学)

Bennet Gebken

AI总结:

本文通过Goldstein子微分分析非光滑优化中(ε,δ)临界点与最小值的距离收敛速度,并应用于梯度采样方法,通过实例验证理论结果。

摘要:

Goldstein ε-子微分是Clarke子微分的放松版本,最近出现在非光滑优化的多个算法中。它伴随着(ε,δ)临界点的概念,即在ε-子微分中具有最小范数的元素范数至多为δ的点。为了获得经典意义下的临界点,ε和δ必须消失。在本文中,我们分析(ε,δ)临界点到最小值的距离如何随着ε和δ消失而变化。随后,我们将结果应用于梯度采样方法并进行数值实验。在整个文章中,我们特别强调通过简单的例子来支持理论结果。

英文摘要:

The Goldstein $\varepsilon$-subdifferential is a relaxed version of the Clarke subdifferential which has recently appeared in several algorithms for nonsmooth optimization. With it comes the notion of $(\varepsilon,δ)$-critical points, which are points in which the element with the smallest norm in the $\varepsilon$-subdifferential has norm at most $δ$. To obtain points that are critical in the classical sense, $\varepsilon$ and $δ$ must vanish. In this article, we analyze at which speed the distance of $(\varepsilon,δ)$-critical points to the minimum vanishes with respect to $\varepsilon$ and $δ$. Afterwards, we apply our results to gradient sampling methods and perform numerical experiments. Throughout the article, we put a special emphasis on supporting the theoretical results with simple examples that visualize them.

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。

↑