Linear Programs (LP) are celebrated widely, particularly so in machine learning where they have allowed for effectively solving probabilistic inference tasks or imposing structure on end-to-end learning systems. Their potential might seem depleted but we propose a foundational, causal perspective that reveals intriguing intra- and inter-structure relations for LP components. We conduct a systematic, empirical investigation on general-, shortest path- and energy system LPs.
@article{arxiv.2203.15274,
title = {Finding Structure and Causality in Linear Programs},
author = {Matej Zečević and Florian Peter Busch and Devendra Singh Dhami and Kristian Kersting},
journal= {arXiv preprint arXiv:2203.15274},
year = {2022}
}