Convergence of the Gradient Sampling Algorithm on Directionally Lipschitz Functions

Convergence of the Gradient Sampling Algorithm on Directionally Lipschitz Functions
复制标题

定向Lipschitz函数梯度采样算法的收敛性

DOI:
10.1007/s11228-021-00610-3
复制
发表时间:
2022
期刊:
Setvalued and variational analysis
影响因子:
--
通讯作者:
Q. Lin
Q. Lin
中科院分区:
--
文献类型:
--
作者:
J. V. Burke;Q. Lin

文献摘要

参考文献

被引文献

相似文献

将梯度采样算法的收敛性理论推广到方向Lipschitz函数。虽然方向Lipschitz函数不一定是局部Lipschitz,但它们几乎处处可微,并且可以很好地近似梯度,因此是梯度采样算法应用的自然候选者。这种扩展的主要障碍是潜在的无界性或空的克拉克次微分的兴趣点。我们提出的收敛性分析提供了一种解决这些问题的途径。特别是,我们恢复通常的收敛理论时,功能是局部Lipschitz。此外,如果算法不将临界性的某个度量驱动到零,则迭代必须收敛到一个点,在该点处,克拉克次微分为空,或者最速下降方向退化,因为它确实位于正则次导数的域的内部。
The convergence theory for the gradient sampling algorithm is extended to directionally Lipschitz functions. Although directionally Lipschitz functions are not necessarily locally Lipschitz, they are almost everywhere differentiable and well approximated by gradients and so are a natural candidate for the application of the gradient sampling algorithm. The main obstacle to this extension is the potential unboundedness or emptiness of the Clarke subdifferential at points of interest. The convergence analysis we present provides one path to addressing these issues. In particular, we recover the usual convergence theory when the function is locally Lipschitz. Moreover, if the algorithm does not drive a certain measure of criticality to zero, then the iterates must converge to a point at which either the Clarke subdifferential is empty or the direction of steepest descent is degenerate in the sense that it does lie in the interior of the domain of the regular subderivative.
通过静态输出反馈和低阶控制器实现鲁棒稳定的非平滑、非凸优化方法
DOI: 10.1016/s1474-6670(17)35659-8
发表时间: 2003
期刊: IFAC Proceedings Volumes
影响因子: --
作者:
J. Burke;A. Lewis;M. Overton
通讯作者: M. Overton
DOI: --
发表时间: 2012
期刊:
影响因子: --
作者:
A. Bressan
通讯作者: A. Bressan
DOI: --
发表时间: 1983
期刊:
影响因子: --
作者:
J. Burke
通讯作者: J. Burke
重温弱锐最小值,第二部分
DOI: --
发表时间: 2005
期刊:
影响因子: --
作者:
V. BurkeJames;DengSien
通讯作者: DengSien