Second-order methods for provably escaping strict saddle points in composite nonconvex and nonsmooth optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bodard, Alexander, Ahookhosh, Masoud, Patrinos, Panagiotis
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909663021236224
author Bodard, Alexander
Ahookhosh, Masoud
Patrinos, Panagiotis
author_facet Bodard, Alexander
Ahookhosh, Masoud
Patrinos, Panagiotis
contents This study introduces two second-order methods designed to provably avoid saddle points in composite nonconvex optimization problems: (i) a nonsmooth trust-region method and (ii) a curvilinear linesearch method. These developments are grounded in the forward-backward envelope (FBE), for which we analyze the local second-order differentiability around critical points and establish a novel equivalence between its second-order stationary points and those of the original objective. We show that the proposed algorithms converge to second-order stationary points of the FBE under a mild local smoothness condition on the proximal mapping of the nonsmooth term. Notably, for \( \C^2 \)-partly smooth functions, this condition holds under a standard strict complementarity assumption. To the best of our knowledge, these are the first second-order algorithms that provably escape nonsmooth strict saddle points of composite nonconvex optimization, regardless of the initialization. Our preliminary numerical experiments show promising performance of the developed methods, validating our theoretical foundations.
format Preprint
id arxiv_https___arxiv_org_abs_2506_22332
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Second-order methods for provably escaping strict saddle points in composite nonconvex and nonsmooth optimization
Bodard, Alexander
Ahookhosh, Masoud
Patrinos, Panagiotis
Optimization and Control
This study introduces two second-order methods designed to provably avoid saddle points in composite nonconvex optimization problems: (i) a nonsmooth trust-region method and (ii) a curvilinear linesearch method. These developments are grounded in the forward-backward envelope (FBE), for which we analyze the local second-order differentiability around critical points and establish a novel equivalence between its second-order stationary points and those of the original objective. We show that the proposed algorithms converge to second-order stationary points of the FBE under a mild local smoothness condition on the proximal mapping of the nonsmooth term. Notably, for \( \C^2 \)-partly smooth functions, this condition holds under a standard strict complementarity assumption. To the best of our knowledge, these are the first second-order algorithms that provably escape nonsmooth strict saddle points of composite nonconvex optimization, regardless of the initialization. Our preliminary numerical experiments show promising performance of the developed methods, validating our theoretical foundations.
title Second-order methods for provably escaping strict saddle points in composite nonconvex and nonsmooth optimization
topic Optimization and Control
url https://arxiv.org/abs/2506.22332