A Framework for Data-Driven Explainability in Mathematical Optimization

0Citations
Citations of this article
13Readers
Mendeley users who have this article in their library.

Abstract

Advancements in mathematical programming have made it possible to efficiently tackle large-scale real-world problems that were deemed intractable just a few decades ago. However, provably optimal solutions may not be accepted due to the perception of optimization software as a black box. Although well understood by scientists, this lacks easy accessibility for practitioners. Hence, we advocate for introducing the explainability of a solution as another evaluation criterion, next to its objective value, which enables us to find tradeoff solutions between these two criteria. Explainability is attained by comparing against (not necessarily optimal) solutions that were implemented in similar situations in the past. Thus, solutions are preferred that exhibit similar features. Although we prove that already in simple cases the explainable model is NP-hard, we characterize relevant polynomially solvable cases such as the explainable shortest path problem. Our numerical experiments on both artificial as well as real-world road networks show the resulting Pareto front. It turns out that the cost of enforcing explainability can be very small.

Cite

CITATION STYLE

APA

Aigner, K. M., Goerigk, M., Hartisch, M., Liers, F., & Miehlich, A. (2024). A Framework for Data-Driven Explainability in Mathematical Optimization. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 38, pp. 20912–20920). Association for the Advancement of Artificial Intelligence. https://doi.org/10.1609/aaai.v38i19.30081

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free