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

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.

arXiv comment19 pages

References in corpus (5)

• Newton-Type Methods for Non-Convex Optimization Under Inexact Hessian Information
• Convergence Rate Analysis of a Stochastic Trust Region Method via Submartingales
• Stochastic Second-order Methods for Non-convex Optimization with Inexact Hessian and Gradient
• Adaptive Regularization Algorithms with Inexact Evaluations for Nonconvex Optimization
• A note on solving nonlinear optimization problems in variable precision

Cited by in corpus (1)

• Learnable Descent Algorithm for Nonsmooth Nonconvex Image Reconstruction