HUANet: Hard-Constrained Unrolled ADMM for Constrained Convex Optimization

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Tran, Trinh, Nguyen, Binh, Nghiem, Truong X.
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914473459056640
author Tran, Trinh
Nguyen, Binh
Nghiem, Truong X.
author_facet Tran, Trinh
Nguyen, Binh
Nghiem, Truong X.
contents This paper presents HUANet, a constrained deep neural network architecture that unrolls the iterations of the Alternating Direction Method of Multipliers (ADMM) into a trainable neural network for solving constrained convex optimization problems. Existing end-to-end learning methods operate as black-box mappings from parameters to solutions, often lacking explicit optimality principles and failing to enforce constraints. To address this limitation, we unroll ADMM and embed a hard-constrained neural network at each iteration to accelerate the algorithm, where equality constraints are enforced via a differentiable correction stage at the network output. Furthermore, we incorporate first-order optimality conditions as soft constraints during training to promote the convergence of the proposed unrolled algorithm. Extensive numerical experiments are conducted to validate the effectiveness of the proposed architecture for constrained optimization problems.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13179
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HUANet: Hard-Constrained Unrolled ADMM for Constrained Convex Optimization
Tran, Trinh
Nguyen, Binh
Nghiem, Truong X.
Optimization and Control
Machine Learning
Systems and Control
This paper presents HUANet, a constrained deep neural network architecture that unrolls the iterations of the Alternating Direction Method of Multipliers (ADMM) into a trainable neural network for solving constrained convex optimization problems. Existing end-to-end learning methods operate as black-box mappings from parameters to solutions, often lacking explicit optimality principles and failing to enforce constraints. To address this limitation, we unroll ADMM and embed a hard-constrained neural network at each iteration to accelerate the algorithm, where equality constraints are enforced via a differentiable correction stage at the network output. Furthermore, we incorporate first-order optimality conditions as soft constraints during training to promote the convergence of the proposed unrolled algorithm. Extensive numerical experiments are conducted to validate the effectiveness of the proposed architecture for constrained optimization problems.
title HUANet: Hard-Constrained Unrolled ADMM for Constrained Convex Optimization
topic Optimization and Control
Machine Learning
Systems and Control
url https://arxiv.org/abs/2604.13179