A Superlinear Convergence Framework for Kurdyka-{\L}ojasiewicz Optimization
Abstract
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 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 . We justify that any sequence conforming to this framework is globally convergent when is a Kurdyka-{\L}ojasiewicz (KL) function, and the convergence has a Q-superlinear rate of order when is a KL function of exponent . Then, we illustrate that the iterate sequence generated by an inexact -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 for an inexact cubic regularization method to solve this class of composite problems with KL property of exponent .
Cite
@article{arxiv.2210.12449,
title = {A Superlinear Convergence Framework for Kurdyka-{\L}ojasiewicz Optimization},
author = {Yitian Qian and Shaohua Pan},
journal= {arXiv preprint arXiv:2210.12449},
year = {2023}
}