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

MaRDI QIDQ6414773zbMATH OpenFDO

Authors Yitian Qian, Shaohua Pan

Publication date 22 October 2022

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 $Phi$ so that the generated sequence possesses a Q-superlinear convergence rate. This framework consists of a monotone decrease condition and a relative error condition, both involving a parameter $p!>0$. We justify that any sequence conforming to this framework is globally convergent when $Phi$ is a KL function, and the convergence has a Q-superlinear rate of order $fracpheta(1+p)$ when $Phi$ is a KL function of exponent $hetain(0,fracpp+1)$. In particular, we propose an inexact proximal Newton method with a $qin[2,3]$-order regularization term for nonconvex and nonsmooth composite problems and show that its iterate sequence 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 $1/2$.

This page was built for publication: A Superlinear Convergence Framework for Kurdyka-{\L}ojasiewicz Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6414773)