Confidence Threshold Neural Diving

TL;DR

This paper introduces a neural diving heuristic that uses confidence thresholds to improve solution quality in mixed integer programming, demonstrating competitive results in a major competition.

Contribution

It proposes a novel confidence threshold technique for neural diving heuristics, enhancing the flexibility and effectiveness of solving mixed integer programs.

Findings

Confidence threshold technique improves primal objective values.

Method achieved 2nd place in NeurIPS 2021 ML4CO competition.

Outperforms other learning-based methods in the competition.

Abstract

Finding a better feasible solution in a shorter time is an integral part of solving Mixed Integer Programs. We present a post-hoc method based on Neural Diving to build heuristics more flexibly. We hypothesize that variables with higher confidence scores are more definite to be included in the optimal solution. For our hypothesis, we provide empirical evidence that confidence threshold technique produces partial solutions leading to final solutions with better primal objective values. Our method won 2nd place in the primal task on the NeurIPS 2021 ML4CO competition. Also, our method shows the best score among other learning-based methods in the competition.