Aigner KM, Goerigk M, Hartisch M, Liers F, Miehlich A (2024)
Publication Language: English
Publication Status: Accepted
Publication Type: Conference contribution, Conference Contribution
Future Publication Type: Conference contribution
Publication year: 2024
Series: The 38th Annual AAAI Conference on Artificial Intelligence
Book Volume: 38
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 trade-off 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.
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 The 38th Annual AAAI Conference on Artificial Intelligence. Vancouver, CA.
Aigner, Kevin-Martin, et al. "A Framework for Data-driven Explainability in Mathematical Optimization." Proceedings of the The 38th Annual AAAI Conference on Artificial Intelligence, Vancouver 2024.