Enregistré dans:
Détails bibliographiques
Auteurs principaux: Agyeman, Bernard T., Li, Zhe, Mitrai, Ilias, Daoutidis, Prodromos
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.22107
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908990213980160
author Agyeman, Bernard T.
Li, Zhe
Mitrai, Ilias
Daoutidis, Prodromos
author_facet Agyeman, Bernard T.
Li, Zhe
Mitrai, Ilias
Daoutidis, Prodromos
contents We propose a hybrid reinforcement and self-supervised learning framework for accelerating generalized Benders decomposition (GBD). In this framework, a graph based reinforcement learning agent operates on a bipartite representation of the master problem and, together with a verification mechanism, determines the integer variable assignments that solve the master problem. These assignments are then used as inputs to a KKT informed neural network, trained via self supervision to predict primal dual solutions that approximately satisfy the Karush Kuhn Tucker conditions of the subproblem. The predicted solutions are used to construct Benders cuts directly. The framework is evaluated on a mixed integer nonlinear programming case study, where it achieves a 57.5% reduction in solution time relative to classical GBD while consistently recovering optimal solutions across all test instances.
format Preprint
id arxiv_https___arxiv_org_abs_2604_22107
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Hybrid Reinforcement and Self-Supervised Learning Aided Benders Decomposition Algorithm
Agyeman, Bernard T.
Li, Zhe
Mitrai, Ilias
Daoutidis, Prodromos
Systems and Control
We propose a hybrid reinforcement and self-supervised learning framework for accelerating generalized Benders decomposition (GBD). In this framework, a graph based reinforcement learning agent operates on a bipartite representation of the master problem and, together with a verification mechanism, determines the integer variable assignments that solve the master problem. These assignments are then used as inputs to a KKT informed neural network, trained via self supervision to predict primal dual solutions that approximately satisfy the Karush Kuhn Tucker conditions of the subproblem. The predicted solutions are used to construct Benders cuts directly. The framework is evaluated on a mixed integer nonlinear programming case study, where it achieves a 57.5% reduction in solution time relative to classical GBD while consistently recovering optimal solutions across all test instances.
title A Hybrid Reinforcement and Self-Supervised Learning Aided Benders Decomposition Algorithm
topic Systems and Control
url https://arxiv.org/abs/2604.22107