Deep learning enhanced mixed integer optimization: Learning to reduce model dimensionality
This addresses computational bottlenecks for optimization problems in fields like supply chain management, but it appears incremental as it applies existing deep learning methods to a known bottleneck in MIP.
The paper tackles the computational complexity of Mixed-Integer Programming (MIP) models by using deep learning to estimate binary variables and reduce model dimensionality, resulting in reduced MIP models solved with standard solvers, though no concrete numbers are provided for performance gains.
This work introduces a framework to address the computational complexity inherent in Mixed-Integer Programming (MIP) models by harnessing the potential of deep learning. By employing deep learning, we construct problem-specific heuristics that identify and exploit common structures across MIP instances. We train deep learning models to estimate complicating binary variables for target MIP problem instances. The resulting reduced MIP models are solved using standard off-the-shelf solvers. We present an algorithm for generating synthetic data enhancing the robustness and generalizability of our models across diverse MIP instances. We compare the effectiveness of (a) feed-forward neural networks (ANN) and (b) convolutional neural networks (CNN). To enhance the framework's performance, we employ Bayesian optimization for hyperparameter tuning, aiming to maximize the occurrence of global optimum solutions. We apply this framework to a flow-based facility location allocation MIP formulation that describes long-term investment planning and medium-term tactical scheduling in a personalized medicine supply chain.