Coherent Local Explanations for Mathematical Optimization
This addresses the need for transparent explanations in optimization algorithms, which is incremental as it builds on existing explainable AI methods by incorporating optimization structure.
The paper tackles the problem of explaining decisions from mathematical optimization algorithms by introducing CLEMO, a method that provides coherent local explanations for multiple model components, and demonstrates its effectiveness on shortest path, knapsack, and vehicle routing problems.
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.