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

• URL: http://arxiv.org/abs/2506.00362v1
• Date: Sat, 31 May 2025 03:05:29 GMT
• Title: FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees
• Authors: Hoang T. Nguyen, Priya L. Donti,
• Abstract summary: Traditional solvers are often computationally prohibitive for real-time use.<n>Machine learning-based approaches have emerged as an alternative, but they struggle to strictly enforce constraints.<n>We propose the Feasibility-Seeking-Integrated Network (FSNet) to ensure constraint satisfaction.
• Score: 3.345575993695074
• License: http://creativecommons.org/licenses/by/4.0/
• 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-Integrated 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.

Related papers

• Towards graph neural networks for provably solving convex optimization problems [5.966097889241178]
  We propose an iterative MPNN framework to solve convex optimization problems with provable feasibility guarantees.<n> Experimental results show that our approach outperforms existing neural baselines in solution quality and feasibility.
  arXiv  Detail & Related papers  (2025-02-04T16:11:41Z)
• Differentiable Projection-based Learn to Optimize in Wireless Network-Part I: Convex Constrained (Non-)Convex Programming [15.689556794350674]
  This paper addresses a class of (non-)feasible optimization problems subject to general convex constraints.<n>Traditional convex optimization methods often struggle to efficiently handle these problems in their most general form.
  arXiv  Detail & Related papers  (2025-01-29T11:52:27Z)
• Self-Supervised Learning of Iterative Solvers for Constrained Optimization [0.0]
  We propose a learning-based iterative solver for constrained optimization. It can obtain very fast and accurate solutions by customizing the solver to a specific parametric optimization problem. A novel loss function based on the Karush-Kuhn-Tucker conditions of optimality is introduced, enabling fully self-supervised training of both neural networks.
  arXiv  Detail & Related papers  (2024-09-12T14:17:23Z)
• Learning Joint Models of Prediction and Optimization [56.04498536842065]
  Predict-Then-Then framework uses machine learning models to predict unknown parameters of an optimization problem from features before solving. This paper proposes an alternative method, in which optimal solutions are learned directly from the observable features by joint predictive models.
  arXiv  Detail & Related papers  (2024-09-07T19:52:14Z)
• Learning Constrained Optimization with Deep Augmented Lagrangian Methods [54.22290715244502]
  A machine learning (ML) model is trained to emulate a constrained optimization solver. This paper proposes an alternative approach, in which the ML model is trained to predict dual solution estimates directly. It enables an end-to-end training scheme is which the dual objective is as a loss function, and solution estimates toward primal feasibility, emulating a Dual Ascent method.
  arXiv  Detail & Related papers  (2024-03-06T04:43:22Z)
• BalMCTS: Balancing Objective Function and Search Nodes in MCTS for Constraint Optimization Problems [7.196057722218442]
  Constraint Problems Optimization (COP) pose intricate challenges in problems usually addressed through Branch and Bound (B&B) methods. We propose a novel neural network algorithm based on a depth-first search algorithm for solving COP. Our method identifies feasible solutions with a gap of less than 17.63% within the initial 5 feasible solutions.
  arXiv  Detail & Related papers  (2023-12-26T03:09:08Z)
• Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets [86.43523688236077]
  Combinatorial optimization (CO) problems are often NP-hard and out of reach for exact algorithms. GFlowNets have emerged as a powerful machinery to efficiently sample from composite unnormalized densities sequentially. In this paper, we design Markov decision processes (MDPs) for different problems and propose to train conditional GFlowNets to sample from the solution space.
  arXiv  Detail & Related papers  (2023-05-26T15:13:09Z)
• Multiobjective variational quantum optimization for constrained problems: an application to Cash Management [45.82374977939355]
  We introduce a new method for solving optimization problems with challenging constraints using variational quantum algorithms. We test our proposal on a real-world problem with great relevance in finance: the Cash Management problem. Our empirical results show a significant improvement in terms of the cost of the achieved solutions, but especially in the avoidance of local minima.
  arXiv  Detail & Related papers  (2023-02-08T17:09:20Z)
• Learning Proximal Operators to Discover Multiple Optima [66.98045013486794]
  We present an end-to-end method to learn the proximal operator across non-family problems. We show that for weakly-ized objectives and under mild conditions, the method converges globally.
  arXiv  Detail & Related papers  (2022-01-28T05:53:28Z)
• Combining Deep Learning and Optimization for Security-Constrained Optimal Power Flow [94.24763814458686]
  Security-constrained optimal power flow (SCOPF) is fundamental in power systems. Modeling of APR within the SCOPF problem results in complex large-scale mixed-integer programs. This paper proposes a novel approach that combines deep learning and robust optimization techniques.
  arXiv  Detail & Related papers  (2020-07-14T12:38:21Z)
• Optimizing Wireless Systems Using Unsupervised and Reinforced-Unsupervised Deep Learning [96.01176486957226]
  Resource allocation and transceivers in wireless networks are usually designed by solving optimization problems. In this article, we introduce unsupervised and reinforced-unsupervised learning frameworks for solving both variable and functional optimization problems.
  arXiv  Detail & Related papers  (2020-01-03T11:01:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.