Global Complexity Bound of a Proximal ADMM for Linearly Constrained Nonseparable Nonconvex Composite Programming
SIAM Journal on Optimization · 31.03.2024 · 34 (1) · 201-224
DOI: 10.1137/22m1503129 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Optimization, online erschienen am 11.01.2024. Verfasst von Weiwei Kong und 1 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 32 Literaturangaben. Gefördert von: Exascale Computing Project, Air Force Office of Scientific Research, Office of Naval Research.
Abstract (Originalsprache)
This paper proposes and analyzes a dampened proximal alternating direction method of multipliers (DP.ADMM) for solving linearly constrained nonconvex optimization problems where the smooth part of the objective function is nonseparable. Each iteration of DP.ADMM consists of (i) a sequence of partial proximal augmented Lagrangian (AL) updates, (ii) an under-relaxed Lagrange multiplier update, and (iii) a novel test to check whether the penalty parameter of the AL function should be updated. Under a basic Slater point condition and some requirements on the dampening factor and under-relaxation parameter, it is shown that DP.ADMM obtains an approximate first-order stationary point of the constrained problem in [Formula: see text] iterations for a given numerical tolerance [Formula: see text]. One of the main novelties of the paper is that convergence of the method is obtained without requiring any rank assumptions on the constraint matrices.
Förderung
- Exascale Computing Project
- Air Force Office of Scientific Research
- Office of Naval Research
- National Science Foundation
- U.S. Department of Energy
Zitieren
APA
Kong, W., & Monteiro, R. D. C. (2024). Global Complexity Bound of a Proximal ADMM for Linearly Constrained Nonseparable Nonconvex Composite Programming. SIAM Journal on Optimization, 34(1), 201-224. https://doi.org/10.1137/22m1503129
Vancouver
Kong W, Monteiro RDC. Global Complexity Bound of a Proximal ADMM for Linearly Constrained Nonseparable Nonconvex Composite Programming. SIAM Journal on Optimization. 2024;34(1):201-224. doi:10.1137/22m1503129
BibTeX
@article{Kong2024,
author = {Kong, Weiwei and Monteiro, Renato D. C.},
title = {Global Complexity Bound of a Proximal ADMM for Linearly Constrained Nonseparable Nonconvex Composite Programming},
journal = {SIAM Journal on Optimization},
year = {2024},
volume = {34},
number = {1},
pages = {201--224},
doi = {10.1137/22m1503129}
}
EUVIMED