DC3: A learning method for optimization with hard constraints

Large optimization problems with hard constraints arise in many settings, yet classical solvers are often prohibitively slow, motivating the use of deep networks as cheap \"approximate solvers.\" Unfortunately, naive deep learning approaches typically cannot enforce the hard constraints of such problems, leading to infeasible solutions. In this work, we present Deep Constraint Completion and Correction (DC3), an algorithm to address this challenge. Specifically, this method enforces feasibility via a differentiable procedure, which implicitly completes partial solutions to satisfy equality constraints and unrolls gradient-based corrections to satisfy inequality constraints. We demonstrate the effectiveness of DC3 both in simple quadratic programming tasks and in the real-world setting of AC optimal power flow, where hard constraints encode the physics of the electrical grid. In both cases, DC3 substantially improves runtime over standard solvers, and achieves near-optimal objective values while preserving feasibility.