A Hybrid Learning-to-Optimize Framework for Mixed-Integer Quadratic Programming

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Le, Viet-Anh, Xie, Mu, Mangharam, Rahul
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909038698037248
author Le, Viet-Anh
Xie, Mu
Mangharam, Rahul
author_facet Le, Viet-Anh
Xie, Mu
Mangharam, Rahul
contents In this paper, we propose a learning-to-optimize (L2O) framework to accelerate solving parametric mixed-integer quadratic programming (MIQP) problems, with a particular focus on mixed-integer model predictive control (MI-MPC) applications. The framework learns to predict integer solutions with enhanced optimality and feasibility by integrating supervised learning (for optimality), self-supervised learning (for feasibility), and a differentiable quadratic programming (QP) layer, resulting in a hybrid L2O framework. Specifically, a neural network (NN) is used to learn the mapping from problem parameters to optimal integer solutions, while a differentiable QP layer is integrated to compute the corresponding continuous variables given the predicted integers and problem parameters. Moreover, a hybrid loss function is proposed, which combines a supervised loss with respect to the global optimal solution, and a self-supervised loss derived from the problem's objective and constraints. The effectiveness of the proposed framework is demonstrated on two benchmark MI-MPC problems, with comparative results against purely supervised and self-supervised learning models.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19383
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Hybrid Learning-to-Optimize Framework for Mixed-Integer Quadratic Programming
Le, Viet-Anh
Xie, Mu
Mangharam, Rahul
Systems and Control
In this paper, we propose a learning-to-optimize (L2O) framework to accelerate solving parametric mixed-integer quadratic programming (MIQP) problems, with a particular focus on mixed-integer model predictive control (MI-MPC) applications. The framework learns to predict integer solutions with enhanced optimality and feasibility by integrating supervised learning (for optimality), self-supervised learning (for feasibility), and a differentiable quadratic programming (QP) layer, resulting in a hybrid L2O framework. Specifically, a neural network (NN) is used to learn the mapping from problem parameters to optimal integer solutions, while a differentiable QP layer is integrated to compute the corresponding continuous variables given the predicted integers and problem parameters. Moreover, a hybrid loss function is proposed, which combines a supervised loss with respect to the global optimal solution, and a self-supervised loss derived from the problem's objective and constraints. The effectiveness of the proposed framework is demonstrated on two benchmark MI-MPC problems, with comparative results against purely supervised and self-supervised learning models.
title A Hybrid Learning-to-Optimize Framework for Mixed-Integer Quadratic Programming
topic Systems and Control
url https://arxiv.org/abs/2511.19383