FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees

Hoang T. Nguyen, Priya L. Donti

Keywords: deep learning, optimization, constraint enforcement

TL;DR: This work proposes a new framework to solve parametric optimization problems with guarantees on feasibility and convergence.

Abstract: Efficiently solving constrained optimization problems is crucial for numerous real-world applications, yet traditional solvers are often computationally prohibitive for real-time use. Machine learning-based approaches have emerged as a promising alternative to provide approximate solutions at faster speeds, but they struggle to strictly enforce constraints, leading to infeasible solutions in practice. To address this, we propose the Feasibility-Seeking Neural Network (FSNet), which integrates a feasibility-seeking step directly into its solution procedure to ensure constraint satisfaction. This feasibility-seeking step solves an unconstrained optimization problem that minimizes constraint violations in a differentiable manner, enabling end-to-end training and providing guarantees on feasibility and convergence. Our experiments across a range of different optimization problems, including both smooth/nonsmooth and convex/nonconvex problems, demonstrate that FSNet can provide feasible solutions with solution quality comparable to (or in some cases better than) traditional solvers, at significantly faster speeds.

Primary Area: Optimization (e.g., convex and non-convex, stochastic, robust)

Submission Number: 17544