cs.LGNov 6, 2026

Solver-Free Decision-Focused Learning via Neural Optimization Layers for Edge Selection

Authors: Xinda Zheng, Frits de Nijs, Edward Lam

Organizations: Department of Data Science and AI, Faculty of Information Technology, Monash University, Clayton, 3800, Victoria, Australia · ARC Training Centre in Optimisation Technologies, Integrated Methodologies, and Applications (OPTIMA), Melbourne, 3000, Victoria, Australia

Abstract

Decision-focused learning trains prediction models to improve downstream decisions, but many methods require costly solver calls or optimal-solution labels. We propose a solver-free decision-focused learning framework for NP-hard edge-selection problems with uncertain parameters in the objective, the constraints, or both. A neural optimization layer is first trained without solution labels, using problem objectives and constraint penalties. Graph-informed edge scoring and iterative refinement encourage concentrated and structurally consistent continuous decisions. The layer is then frozen, and a prediction model is trained through its continuous output using a problem-specific loss evaluated under observed parameters. At deployment, the predictor, optimization layer, and a lightweight decoder produce decisions without solving the original NP-hard problem. Experiments on the asymmetric traveling salesperson and endpoint-free orienteering problems show consistently better decision quality than prediction-focused learning and improvements over most evaluated decision-focused baselines. Our framework requires less training time than the evaluated decision-focused baselines, even when optimization-layer pretraining is included. Neural deployment also produces decisions faster than solver-based deployment, offering a better quality-efficiency trade-off. The layer also reduces training cost in existing decision-focused methods when used as an approximate optimization oracle.

Figures & tables

Explore similar work

CardsList
  1. A Solver-Free Training Method for Predict-then-Optimize

    Jun 17, 2026Beichen Wan, Mo LiuPredict-Then-OptimizeLearning to Optimize

  2. Scaling Decision-Focused Learning to Large Problems with Lagrangian Decomposition

    Jun 7, 2026Stéphane Eilles-Chan Way, Hugo Percot, Quentin Cappart +2Predict-Then-OptimizeLearning to Optimize

  3. PolyStepOR: Learning to Decide Without Optimal Decisions

    Sep 26, 2026Viet The Nguyen, Gunther Gust, An Thai LeDecision-Focused LearningPredict-Then-Optimize