In this paper, we propose a Pre-trained Mixed Integer Optimization framework (PreMIO) that accelerates online mixed integer program (MIP) solving with offline datasets and machine learning models. Our method is based on a data-driven multi-variable cardinality branching procedure that splits the MIP feasible region using hyperplanes chosen by the concentration inequalities. Unlike most previous ML+MIP approaches that either require complicated implementation or suffer from a lack of theoretical justification, our method is simple, flexible, provable, and explainable. Numerical experiments on both classical OR benchmark datasets and real-life instances validate the efficiency of our proposed method.
@article{arxiv.2305.12352,
title = {Data-driven Mixed Integer Optimization through Probabilistic Multi-variable Branching},
author = {Yanguang Chen and Wenzhi Gao and Wanyu Zhang and Dongdong Ge and Huikang Liu and Yinyu Ye},
journal= {arXiv preprint arXiv:2305.12352},
year = {2025}
}