数学优化的连贯局部解释
Coherent Local Explanations for Mathematical Optimization
AI总结：
针对现有解释方法忽略优化问题结构的问题，提出CLEMO方法，为优化模型的目标值和决策变量提供与模型结构连贯的局部解释，并在最短路径、背包和车辆路径问题上验证了有效性。
摘要：
可解释人工智能方法的兴起旨在增强机器学习模型的透明度和可解释性。与此同时，对于通过数学优化中使用的复杂算法所做出的决策，其解释需求也在日益增长。然而，现有的解释方法并未考虑底层优化问题的结构，导致结果不可靠。针对这一需求，我们提出了数学优化的连贯局部解释（CLEMO）。CLEMO为优化模型的多个组成部分（目标值和决策变量）提供解释，这些解释与底层模型结构保持一致。我们基于采样的程序能够为精确算法和启发式求解算法的行为提供解释。通过在最短路径问题、背包问题和车辆路径问题上的实验，展示了CLEMO的有效性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
