ML-Guided Primal Heuristics for Mixed Binary Quadratic Programs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Weimin, Isenberg, Natalie M., Drgoňa, Ján, Vrabie, Draguna L, Dilkina, Bistra
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917436324839424
author Huang, Weimin
Isenberg, Natalie M.
Drgoňa, Ján
Vrabie, Draguna L
Dilkina, Bistra
author_facet Huang, Weimin
Isenberg, Natalie M.
Drgoňa, Ján
Vrabie, Draguna L
Dilkina, Bistra
contents Mixed Binary Quadratic Programs (MBQPs) are an important and complex set of problems in combinatorial optimization. As solving large-scale combinatorial optimization problems is challenging, primal heuristics have been developed to quickly identify high-quality solutions within a short amount of time. Recently, a growing body of research has also used machine learning to accelerate solution methods for challenging combinatorial optimization problems. Despite the increasing popularity of these ML-guided methods, a large body of work has focused on Mixed-Integer Linear Programs (MILPs). MBQPs are challenging to solve due to the combinatorial complexity coupled with nonlinearities. This work proposes ML-guided primal heuristics for Mixed Binary Quadratic Programs (MBQPs) by adapting and extending existing work on ML-guided MILP solution prediction to MBQPs. We introduce a new neural network architecture for MBQP solution prediction and a new training data collection procedure. Moreover, we extend existing loss functions in solution prediction and propose to combine contrastive and weighted cross-entropy losses. We evaluate the methods on standard and real-world MBQP benchmarks and show that the developed ML-guided methods significantly outperform existing primal heuristics and state-of-the-art solvers. Furthermore, models trained with our proposed extension with combined losses outperform other ML-based methods adapted from MILPs and improve generalization in cross-regional inference on a real-world wind farm layout optimization problem.
format Preprint
id arxiv_https___arxiv_org_abs_2604_23053
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ML-Guided Primal Heuristics for Mixed Binary Quadratic Programs
Huang, Weimin
Isenberg, Natalie M.
Drgoňa, Ján
Vrabie, Draguna L
Dilkina, Bistra
Machine Learning
Optimization and Control
Mixed Binary Quadratic Programs (MBQPs) are an important and complex set of problems in combinatorial optimization. As solving large-scale combinatorial optimization problems is challenging, primal heuristics have been developed to quickly identify high-quality solutions within a short amount of time. Recently, a growing body of research has also used machine learning to accelerate solution methods for challenging combinatorial optimization problems. Despite the increasing popularity of these ML-guided methods, a large body of work has focused on Mixed-Integer Linear Programs (MILPs). MBQPs are challenging to solve due to the combinatorial complexity coupled with nonlinearities. This work proposes ML-guided primal heuristics for Mixed Binary Quadratic Programs (MBQPs) by adapting and extending existing work on ML-guided MILP solution prediction to MBQPs. We introduce a new neural network architecture for MBQP solution prediction and a new training data collection procedure. Moreover, we extend existing loss functions in solution prediction and propose to combine contrastive and weighted cross-entropy losses. We evaluate the methods on standard and real-world MBQP benchmarks and show that the developed ML-guided methods significantly outperform existing primal heuristics and state-of-the-art solvers. Furthermore, models trained with our proposed extension with combined losses outperform other ML-based methods adapted from MILPs and improve generalization in cross-regional inference on a real-world wind farm layout optimization problem.
title ML-Guided Primal Heuristics for Mixed Binary Quadratic Programs
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2604.23053