A mirror inertial forward-reflected-backward splitting: Global convergence and linesearch extension beyond convexity and Lipschitz smoothness
From MaRDI portal
Publication:6507218
DOI10.1007/S10957-024-02383-9arXiv2212.01504MaRDI QIDQ6507218FDOQ6507218
Authors: Ziyuan Wang, Andreas Themelis, Hongjia Ou, Xianfu Wang 
Abstract: This work investigates a Bregman and inertial extension of the forward-reflected-backward algorithm [Y. Malitsky and M. Tam, SIAM J. Optim., 30 (2020), pp. 1451--1472] applied to structured nonconvex minimization problems under relative smoothness. To this end, the proposed algorithm hinges on two key features: taking inertial steps in the dual space, and allowing for possibly negative inertial values. Our analysis begins with studying an associated envelope function that takes inertial terms into account through a novel product space formulation. Such construction substantially differs from similar objects in the literature and could offer new insights for extensions of splitting algorithms. Global convergence and rates are obtained by appealing to the generalized concave Kurdyka-Lojasiewicz (KL) property, which allows us to describe a sharp upper bound on the total length of iterates. Finally, a linesearch extension is given to enhance the proposed method.
Nonconvex programming, global optimization (90C26) Nonsmooth analysis (49J52) Set-valued and variational analysis (49J53)
This page was built for publication: A mirror inertial forward-reflected-backward splitting: Global convergence and linesearch extension beyond convexity and Lipschitz smoothness
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6507218)
