Coherent Local Explanations for Mathematical Optimization

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Otto, Daan, Kurtz, Jannis, Birbil, S. Ilker
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909652152745984
author Otto, Daan
Kurtz, Jannis
Birbil, S. Ilker
author_facet Otto, Daan
Kurtz, Jannis
Birbil, S. Ilker
contents The surge of explainable artificial intelligence methods seeks to enhance transparency and explainability in machine learning models. At the same time, there is a growing demand for explaining decisions taken through complex algorithms used in mathematical optimization. However, current explanation methods do not take into account the structure of the underlying optimization problem, leading to unreliable outcomes. In response to this need, we introduce Coherent Local Explanations for Mathematical Optimization (CLEMO). CLEMO provides explanations for multiple components of optimization models, the objective value and decision variables, which are coherent with the underlying model structure. Our sampling-based procedure can provide explanations for the behavior of exact and heuristic solution algorithms. The effectiveness of CLEMO is illustrated by experiments for the shortest path problem, the knapsack problem, and the vehicle routing problem.
format Preprint
id arxiv_https___arxiv_org_abs_2502_04840
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Coherent Local Explanations for Mathematical Optimization
Otto, Daan
Kurtz, Jannis
Birbil, S. Ilker
Optimization and Control
Machine Learning
The surge of explainable artificial intelligence methods seeks to enhance transparency and explainability in machine learning models. At the same time, there is a growing demand for explaining decisions taken through complex algorithms used in mathematical optimization. However, current explanation methods do not take into account the structure of the underlying optimization problem, leading to unreliable outcomes. In response to this need, we introduce Coherent Local Explanations for Mathematical Optimization (CLEMO). CLEMO provides explanations for multiple components of optimization models, the objective value and decision variables, which are coherent with the underlying model structure. Our sampling-based procedure can provide explanations for the behavior of exact and heuristic solution algorithms. The effectiveness of CLEMO is illustrated by experiments for the shortest path problem, the knapsack problem, and the vehicle routing problem.
title Coherent Local Explanations for Mathematical Optimization
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2502.04840