We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
An extrapolated proximal iteratively reweighted method for nonconvex composite optimization problems.
- Authors
Ge, Zhili; Wu, Zhongming; Zhang, Xin; Ni, Qin
- Abstract
We consider a class of problems where the objective function is the sum of a smooth function and a composition of nonconvex and nonsmooth functions. Such optimization problems arise frequently in machine learning and data processing. The proximal iteratively reweighted method has been widely used and popularized in solving these problems. In this paper, we develop an extrapolated proximal iteratively reweighted method that incorporates two different flexible inertial steps at each iteration. We first prove the subsequential convergence of the proposed method under parameter constraints. Moreover, if the objective function satisfies the Kurdyka-Łojasiewicz property, the global convergence of the new method is established. In addition, we analyze the local convergence rate by making assumptions on the Kurdyka-Łojasiewicz exponent of the objective function. Finally, numerical results on l p minimization and feature selection problems are reported to show the effectiveness and superiority of the proposed algorithm.
- Subjects
FEATURE selection; SMOOTHNESS of functions; MACHINE learning; ELECTRONIC data processing; PROBLEM solving; NONCONVEX programming; NONSMOOTH optimization
- Publication
Journal of Global Optimization, 2023, Vol 86, Issue 4, p821
- ISSN
0925-5001
- Publication type
Article
- DOI
10.1007/s10898-023-01299-4