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 2402.09831math.OC
收藏

关于约束优化中平稳性的一则注记

A note on stationarity in constrained optimization

Edouard Pauwels

AI总结:

该约束优化研究指出通用情形下临界性是合适的平稳性概念,但实际场景中Fréchet平稳性更典型,通过半代数集上函数临界点性质、投影梯度算法聚点性质两个结果给出简洁自包含的论证。

摘要:

在闭子集C上最小化光滑函数f会引出不同的平稳性概念:具有强变分意义的Fréchet(弗雷歇)平稳性,以及通过闭包过程定义、涉及极限次微分(即Mordukovitch(莫尔杜霍维奇)次微分)概念的临界性。后者是一种最优性条件,在某些情形下可能失去Fréchet平稳性的变分含义。本注记旨在说明,尽管临界性是完全通用情形下的合适概念,但Fréchet平稳性在实际场景中是典型存在的。我们汇总了两个结果来阐释这一现象。这些结果本质上是已知的,我们的目标是在约束优化框架下提供简洁且自包含的论证。首先我们证明,若C是半代数的,则对一般的光滑半代数函数f,f在C上的所有临界点实际上都是Fréchet平稳的。其次我们证明,对于小步长,投影梯度算法的所有聚点都是Fréchet平稳的,且带有余项的显式全局二次估计,可避开非Fréchet平稳的潜在临界点以及一些不良局部极小值。

英文摘要:

Minimizing a smooth function f on a closed subset C leads to different notions of stationarity: Fr{é}chet stationarity, which carries a strong variational meaning, and criticality, which is defined through a closure process and involves the notion of limiting, or Mordukovitch, subdifferential. The latter is an optimality condition which may loose the variational meaning of Fr{é}chet stationarity in some settings. The purpose of this note is to illustrate that, while criticality is the appropriate notion in full generality, Fr{é}chet stationarity is typical in practical scenarios.We gather two results to illustrate this phenomenon. These results are essentially known and, our goal is to provide consize self contained arguments in the constrained optimization setting. First we show that if C is semi-algebraic, then for a generic smooth semi-algebraic function f , all critical points of f on C are actually Fr{é}chet stationary. Second we prove that for small step-sizes, all the accumulation points of the projected gradient algorithm are Fr{é}chet stationary, with an explicit global quadratic estimate of the remainder, avoiding potential critical points that are not Fr{é}chet stationary, and some bad local minima.

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。

↑