HUANet: Hard-Constrained Unrolled ADMM for Constrained Convex Optimization
Provides a principled deep learning approach for constrained optimization, improving reliability and speed for applications requiring strict constraint enforcement.
HUANet unrolls ADMM iterations into a trainable neural network with hard constraints for constrained convex optimization, achieving faster convergence and constraint satisfaction compared to black-box methods.
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.