arXiv：cs.LG（机器学习，全量分类）· Trinh Tran, Binh Nguyen, Truong X. Nghiem·· 17 小时前AI 评分28
HUANet：面向约束凸优化的硬约束展开 ADMM 网络
HUANet: Hard-Constrained Unrolled ADMM for Constrained Convex Optimization
AI 导读
HUANet 将 ADMM 展开为可训练神经网络，用于加速参数化约束凸优化求解。它在每次展开迭代中嵌入硬约束神经网络，通过可微校正阶段强制满足原问题的仿射等式约束，并将一阶最优性条件纳入自监督训练损失以促进收敛。在基准优化问题与控制应用上的数值实验验证了其加速效果。
正文
Abstract:This paper presents HUANet, a constrained deep neural network architecture that unrolls the Alternating Direction Method of Multipliers (ADMM) into a trainable neural network for accelerating parametric constrained convex optimization. Existing end-to-end learning methods operate as black-box mappings from parameters to solutions, often without explicitly incorporating optimality principles or guaranteeing constraint satisfaction. To address these limitations, HUANet embeds a hard-constrained neural network within each unrolled ADMM iteration, where a differentiable correction stage enforces the affine equalities of the primal subproblem. Furthermore, we incorporate first-order optimality conditions into a self-supervised training loss to promote the convergence of the proposed unrolled algorithm. Extensive numerical experiments for benchmark optimization problems and a control application demonstrate and validate the effectiveness of HUANet in accelerating constrained convex optimization solving.
| Subjects: | Optimization and Control (math.OC); Machine Learning (cs.LG); Systems and Control (eess.SY) |
| Cite as: | arXiv:2604.13179 [math.OC] |
| (or arXiv:2604.13179v2 [math.OC] for this version) | |
| https://doi.org/10.48550/arXiv.2604.13179 arXiv-issued DOI via DataCite |
Submission history
From: Trinh Tran [view email]
[v1]
Tue, 14 Apr 2026 18:01:48 UTC (187 KB)
[v2]
Wed, 30 Sep 2026 18:48:54 UTC (193 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org