pith. sign in

arxiv: 1902.10406 · v1 · pith:I4BZ27AUnew · submitted 2019-02-27 · 🧮 math.OC

Minimization of nonsmooth nonconvex functions using inexact evaluations and its worst-case complexity

classification 🧮 math.OC
keywords epsilonevaluationsnonconvexalgorithmcomplexityinexactnonsmoothbound
0
0 comments X
read the original abstract

An adaptive regularization algorithm using inexact function and derivatives evaluations is proposed for the solution of composite nonsmooth nonconvex optimization. It is shown that this algorithm needs at most $O(|\log(\epsilon)|\,\epsilon^{-2})$ evaluations of the problem's functions and their derivatives for finding an $\epsilon$-approximate first-order stationary point. This complexity bound therefore generalizes that provided by [Bellavia, Gurioli, Morini and Toint, 2018] for inexact methods for smooth nonconvex problems, and is within a factor $|\log(\epsilon)|$ of the optimal bound known for smooth and nonsmooth nonconvex minimization with exact evaluations. A practically more restrictive variant of the algorithm with worst-case complexity $O(|\log(\epsilon)|+\epsilon^{-2})$ is also presented.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.