ML-Guided Primal Heuristics for Mixed Binary Quadratic Programs

TL;DR

This paper introduces machine learning-guided primal heuristics specifically designed for solving complex Mixed Binary Quadratic Programs, demonstrating significant improvements over existing methods and solvers.

Contribution

It develops a new neural network architecture and training procedure tailored for MBQPs, extending ML-guided solution prediction techniques from MILPs.

Findings

ML-guided heuristics outperform existing primal heuristics and solvers.

Models trained with combined loss functions show better generalization and accuracy.

Proposed methods are effective on both standard and real-world MBQP benchmarks.

Abstract

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.