The selection of cuts to be added to the current LP relaxation is one of the most critical task in Branch-and-Cut methods, since it strongly affects the performances of the algorithm. Recently, machine learning techniques have become popular to define effective cut selection strategies. In this paper we explore the possibility of selecting cuts by ranking them via support vector regression.
Machine Learning Techniques for Branch-and-Cut Methods: The Selection of Cutting Planes
Marcello SammarraMembro del Collaboration Group
2025
Abstract
The selection of cuts to be added to the current LP relaxation is one of the most critical task in Branch-and-Cut methods, since it strongly affects the performances of the algorithm. Recently, machine learning techniques have become popular to define effective cut selection strategies. In this paper we explore the possibility of selecting cuts by ranking them via support vector regression.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
PaperNumtaGMS23-R1.pdf
solo utenti autorizzati
Descrizione: This is the Author Accepted Manuscript (postprint) version of the following paper: (Giallombardo, G., Miglionico, G., Sammarra, M. (2025) Machine Learning Techniques for Branch-and-Cut Methods: The Selection of Cutting Planes) peer-reviewed and accepted for publication in (Sergeyev, Y.D., Kvasov, D.E., Astorino, A. (eds) Numerical Computations: Theory and Algorithms. NUMTA 2023. Lecture Notes in Computer Science, vol 14476. Springer, Cham https://doi.org/10.1007/978-3-031-81241-5_25)
Tipologia:
Documento in Post-print
Licenza:
NON PUBBLICO - Accesso privato/ristretto
Dimensione
310.22 kB
Formato
Adobe PDF
|
310.22 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
