ID-PaS+ : Identity-Aware Predict-and-Search for General Mixed-Integer Linear Programs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cai, Junyang, Raqabi, El Mehdi Er, Van Hentenryck, Pascal, Dilkina, Bistra
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911602348916736
author Cai, Junyang
Raqabi, El Mehdi Er
Van Hentenryck, Pascal
Dilkina, Bistra
author_facet Cai, Junyang
Raqabi, El Mehdi Er
Van Hentenryck, Pascal
Dilkina, Bistra
contents Mixed-Integer Linear Programs (MIPs) are powerful and flexible tools for modeling a wide range of real-world combinatorial optimization problems. Predict-and-Search methods operate by using a predictive model to estimate promising variable assignments and then guiding a search procedure toward high-quality solutions. Recent research has demonstrated that incorporating machine learning (ML) into the Predict-and-Search framework significantly enhances its performance. Still, it is restricted to binary-only problems and overlooks the presence of fixed variable structures that commonly arise in real-world settings. This work extends the current Predict-and-Search (PAS) framework to parametric general parametric MIPs and introduces ID-PAS+, an identity-aware learning framework that enables the ML model to handle heterogeneous variable types more effectively. Experiments on several real-world large-scale problems demonstrate that ID-PAS+ consistently achieves superior performance compared to the state-of-the-art solver Gurobi and PAS.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10211
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ID-PaS+ : Identity-Aware Predict-and-Search for General Mixed-Integer Linear Programs
Cai, Junyang
Raqabi, El Mehdi Er
Van Hentenryck, Pascal
Dilkina, Bistra
Artificial Intelligence
Mixed-Integer Linear Programs (MIPs) are powerful and flexible tools for modeling a wide range of real-world combinatorial optimization problems. Predict-and-Search methods operate by using a predictive model to estimate promising variable assignments and then guiding a search procedure toward high-quality solutions. Recent research has demonstrated that incorporating machine learning (ML) into the Predict-and-Search framework significantly enhances its performance. Still, it is restricted to binary-only problems and overlooks the presence of fixed variable structures that commonly arise in real-world settings. This work extends the current Predict-and-Search (PAS) framework to parametric general parametric MIPs and introduces ID-PAS+, an identity-aware learning framework that enables the ML model to handle heterogeneous variable types more effectively. Experiments on several real-world large-scale problems demonstrate that ID-PAS+ consistently achieves superior performance compared to the state-of-the-art solver Gurobi and PAS.
title ID-PaS+ : Identity-Aware Predict-and-Search for General Mixed-Integer Linear Programs
topic Artificial Intelligence
url https://arxiv.org/abs/2512.10211