谷歌浏览器插件
订阅小程序
在清言上使用

A Superlinear Convergence Framework for Kurdyka-{\L}ojasiewicz Optimization

arXiv (Cornell University)(2022)

引用 0|浏览0
暂无评分
摘要
This work extends the iterative framework proposed by Attouch et al. (in Math. Program. 137: 91-129, 2013) for minimizing a nonconvex and nonsmooth function $\Phi$ so that the generated sequence possesses a Q-superlinear convergence rate. This framework consists of a monotone decrease condition, a relative error condition and a continuity condition, and the first two conditions both involve a parameter $p\!>0$. We justify that any sequence conforming to this framework is globally convergent when $\Phi$ is a Kurdyka-{\L}ojasiewicz (KL) function, and the convergence has a Q-superlinear rate of order $\frac{p}{\theta(1+p)}$ when $\Phi$ is a KL function of exponent $\theta\in(0,\frac{p}{p+1})$. Then, we illustrate that the iterate sequence generated by an inexact $q\in[2,3]$-order regularization method for composite optimization problems with a nonconvex and nonsmooth term belongs to this framework, and consequently, first achieve the Q-superlinear convergence rate of order $4/3$ for an inexact cubic regularization method to solve this class of composite problems with KL property of exponent $1/2$.
更多
查看译文
关键词
superlinear convergence,iterative framework,optimization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要