Enregistré dans:
Détails bibliographiques
Auteurs principaux: Greenstein, Dan, Hallak, Nadav
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.22045
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910245082628096
author Greenstein, Dan
Hallak, Nadav
author_facet Greenstein, Dan
Hallak, Nadav
contents This paper addresses the challenge of obtaining strong optimality guarantees in constrained nonsmooth nonconvex optimization under mild regularity conditions, namely local Lipschitz continuity and existence and continuity of directional derivatives. While standard methods typically ensure weak stationarity notions, achieving directional (d-)stationarity remains nontrivial. We show that a random direction exploration step is sufficient to attain d-stationarity. The proposed approach augments any base optimization method with a single exploration step that samples a direction and step size and accepts the candidate based on a function value comparison. The resulting scheme guarantees that all accumulation points are d-stationary almost surely, independently of the behavior of the underlying method. Moreover, it preserves convergence rates of the base method, as established for DCA and prox-linear-type schemes. The theoretical results are complemented by numerical experiments illustrating the effect and guarantees of the exploration step.
format Preprint
id arxiv_https___arxiv_org_abs_2605_22045
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Achieving Directional-Stationarity from a Single Random Direction Step
Greenstein, Dan
Hallak, Nadav
Optimization and Control
This paper addresses the challenge of obtaining strong optimality guarantees in constrained nonsmooth nonconvex optimization under mild regularity conditions, namely local Lipschitz continuity and existence and continuity of directional derivatives. While standard methods typically ensure weak stationarity notions, achieving directional (d-)stationarity remains nontrivial. We show that a random direction exploration step is sufficient to attain d-stationarity. The proposed approach augments any base optimization method with a single exploration step that samples a direction and step size and accepts the candidate based on a function value comparison. The resulting scheme guarantees that all accumulation points are d-stationary almost surely, independently of the behavior of the underlying method. Moreover, it preserves convergence rates of the base method, as established for DCA and prox-linear-type schemes. The theoretical results are complemented by numerical experiments illustrating the effect and guarantees of the exploration step.
title Achieving Directional-Stationarity from a Single Random Direction Step
topic Optimization and Control
url https://arxiv.org/abs/2605.22045