Logo image
A Near-optimal Method for Linearly Constrained Composite Non-convex Non-smooth Problems
Preprint   Open access

A Near-optimal Method for Linearly Constrained Composite Non-convex Non-smooth Problems

Wei Liu, Qihang Lin and Yangyang Xu
ArXiV.org
Cornell University
03/28/2025
DOI: 10.48550/arxiv.2503.22927
url
https://doi.org/10.48550/arxiv.2503.22927View
Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

Abstract

We study first-order methods (FOMs) for solving \emph{composite nonconvex nonsmooth} optimization with linear constraints. Recently, the lower complexity bounds of FOMs on finding an (ε,ε)-KKT point of the considered problem is established in \cite{liu2025lowercomplexityboundsfirstorder}. However, optimization algorithms that achieve this lower bound had not been developed. In this paper, we propose an inexact proximal gradient method, where subproblems are solved using a recovering primal-dual procedure. Without making the bounded domain assumption, we establish that the oracle complexity of the proposed method, for finding an (ε,ε)-KKT point of the considered problem, matches the lower bounds up to a logarithmic factor. Consequently, in terms of the complexity, our algorithm outperforms all existing methods. We demonstrate the advantages of our proposed algorithm over the (linearized) alternating direction method of multipliers and the (proximal) augmented Lagrangian method in the numerical experiments.
Mathematics - Optimization and Control

Details

Metrics

17 Record Views
Logo image