English

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

Systems and Control 2026-05-14 v2 Systems and Control

Abstract

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.

Keywords

Cite

@article{arxiv.2511.19383,
  title  = {A Hybrid Learning-to-Optimize Framework for Mixed-Integer Quadratic Programming},
  author = {Viet-Anh Le and Mu Xie and Rahul Mangharam},
  journal= {arXiv preprint arXiv:2511.19383},
  year   = {2026}
}

Comments

fianl L4DC 2026

R2 v1 2026-07-01T07:52:39.274Z