A Parallel Adaptive Proximal ADMM for Linearly Constrained Separable Composite Optimization Problems
Abstract
We propose and analyze an adaptive proximal alternating direction method of multipliers (ADMM), based on Jacobi-type updates, for linearly constrained separable nonconvex composite optimization problems. The objective consists of two block-separable functions, one continuously differentiable and weakly convex, and the other convex and Lipschitz continuous. The proposed method is adaptive to all problem parameters and allows inexact solutions of the block proximal subproblems. At each iteration, we solve all block subproblems in parallel, then apply a novel test to decide whether to update the Lagrange multiplier and/or the penalty parameter. Without any rank assumptions on the constraint matrices, we establish an cal O(ε−3) iteration-complexity bound for obtaining an approximate first-order stationary point. This matches the best-known complexity for cyclic proximal ADMM methods and improves the existing complexity of Jacobi-type schemes in this general nonconvex setting. Numerical experiments on a nonconvex quadratic program illustrate the proposed method's computational benefits.
Related
- A Novel Solving Method for Multi-Constrained Optimization of Ceramic Composite Armor with Failure Considerations Based on an Improved Response Surface Methodology–Adaptive Moment Estimation (RSM-Adam) Framework
- Envelopt: Constrained Convex Composite Optimization
- Restarted Accelerated Primal-Dual Algorithms with Adaptive Stepsizes for Nonlinear Conic Constrained Convex Optimization
- Consensus-based optimization for linearly separable functions
- Tensor-Train Compressed Separable PINNs: A Curvature-Aware Optimization Framework for Parametric PDEs in High Dimensions
BibTeX
@misc{maia2026parallel,
title = {{A Parallel Adaptive Proximal ADMM for Linearly Constrained Separable Composite Optimization Problems}},
author = {Leandro F. Maia and Renato D. C. Monteiro and Gilson N. Silva},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.00570},
eprint = {2611.00570},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.00570},
}
RIS
TY - UNPB
TI - A Parallel Adaptive Proximal ADMM for Linearly Constrained Separable Composite Optimization Problems
AU - Leandro F. Maia
AU - Renato D. C. Monteiro
AU - Gilson N. Silva
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.00570
UR - https://arxiv.org/abs/2611.00570
AB - We propose and analyze an adaptive proximal alternating direction method of multipliers (ADMM), based on Jacobi-type updates, for linearly constrained separable nonconvex composite optimization problems. The objective consists of two block-separable functions, one continuously differentiable and weakly convex, and the other convex and Lipschitz continuous. The proposed method is adaptive to all problem parameters and allows inexact solutions of the block proximal subproblems. At each iteration, we solve all block subproblems in parallel, then apply a novel test to decide whether to update the Lagrange multiplier and/or the penalty parameter. Without any rank assumptions on the constraint matrices, we establish an cal O(ε^−3) iteration-complexity bound for obtaining an approximate first-order stationary point. This matches the best-known complexity for cyclic proximal ADMM methods and improves the existing complexity of Jacobi-type schemes in this general nonconvex setting. Numerical experiments on a nonconvex quadratic program illustrate the proposed method's computational benefits.
ER -