A superlinearly convergent subgradient method for sharp semismooth problems

Autor:	Charisopoulos, Vasileios, Davis, Damek
Rok vydání:	2022
Předmět:	Mathematics - Optimization and Control 65K05 65K10 90C06 90C30
Druh dokumentu:	Working Paper
Popis:	Subgradient methods comprise a fundamental class of nonsmooth optimization algorithms. Classical results show that certain subgradient methods converge sublinearly for general Lipschitz convex functions and converge linearly for convex functions that grow sharply away from solutions. Recent work has moreover extended these results to certain nonconvex problems. In this work we seek to improve the complexity of these algorithms, asking: is it possible to design a superlinearly convergent subgradient method? We provide a positive answer to this question for a broad class of sharp semismooth functions. Comment: 48 pages, 7 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2201.04611 Zobrazit plný text záznamu View this record from Arxiv