A deep learning approach for solving linear programming problems - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Neurocomputing Année : 2023

A deep learning approach for solving linear programming problems

Résumé

Finding the optimal solution to a linear programming (LP) problem is a long-standing computational problem in Operations Research. This paper proposes a deep learning approach in the form of feed-forward neural networks to solve the LP problem. The latter is first modeled by an ordinary differential equations (ODE) system, the state solution of which globally converges to the optimal solution of the LP problem. A neural network model is constructed as an approximate state solution to the ODE system, such that the neural network model contains the prediction of the LP problem. Furthermore, we extend the capability of the neural network by taking the parameter of LP problems as an input variable so that one neural network can solve multiple LP instances in a one-shot manner. Finally, we validate the proposed method through a collection of specific LP examples and show concretely how the proposed method solves the example.
Fichier principal
Vignette du fichier
No_4__SKI__1st_revision_ (2).pdf (831.8 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04370992 , version 1 (03-01-2024)

Identifiants

Citer

Dawen Wu, Abdel Lisser. A deep learning approach for solving linear programming problems. Neurocomputing, 2023, 520, pp.15-24. ⟨10.1016/j.neucom.2022.11.053⟩. ⟨hal-04370992⟩
6 Consultations
64 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More