Multi-ResNets for Subspace Preconditioning in Constrained Optimization
For practitioners solving constrained optimization problems with priority-ordered constraints, MResOpt offers a method to enforce high-priority constraints more effectively.
MResOpt, a staged residual neural network, improves high-priority constraint satisfaction in constrained optimization problems, achieving substantially lower violation than reprojected baselines on AC optimal power flow while remaining computationally efficient.
We propose MResOpt, a staged residual neural network architecture for constrained optimization problems. Our architecture fits within predict-complete-correct pipelines and decomposes constraint satisfaction by priority through intermediate re-completion and stage-aware losses. The framework enables domain-informed ordered constraint satisfaction which allows the network to utilize ordinal structure when present. Under an idealized infinite-width regime, we show that our design behaves as sequential Gaussian Process regression. On synthetic QP, QCQP, and SOCP benchmarks, the staged architecture improves high-priority constraint satisfaction across convex and non-convex settings. On line-flow-constrained AC optimal power flow, we introduce a physics-motivated constraint ordering and show that MResOpt supports a learned division of labor that keeps iterates on the equality manifold, achieving substantially lower high-priority violation than reprojected baselines while remaining computationally efficient.