标题： 黑箱模型中估计主效应的加速聚合D最优设计 显示英文标题

标题： Accelerated Aggregated D-Optimal Designs for Estimating Main Effects in Black-Box Models

摘要： 监督学习的最新进展推动了对黑箱模型解释的兴趣，特别是通过估计输入变量对模型预测的影响。 然而，现有方法常常面临关键限制，包括可扩展性差、对分布外采样的敏感性以及在相关特征下的不稳定性。 为了解决这些问题，我们提出了A2D2E，这是一种基于$\textbf{E}$的估计器，结合了$\textbf{A}$加速的$\textbf{A}$聚合$\textbf{D}$-最优$\textbf{D}$设计。 我们的方法利用了合理的实验设计，以提高主效应估计的效率和鲁棒性。 我们建立了理论保证，包括收敛性和方差减少，并通过大量模拟验证了A2D2E。 我们进一步通过一个真实数据的案例研究展示了该方法的潜力，并应用于语言模型。 重现结果的代码可在https://github.com/cchihyu/A2D2E找到。 显示英文摘要

摘要： Recent advances in supervised learning have driven growing interest in explaining black-box models, particularly by estimating the effects of input variables on model predictions. However, existing approaches often face key limitations, including poor scalability, sensitivity to out-of-distribution sampling, and instability under correlated features. To address these issues, we propose A2D2E, an $\textbf{E}$stimator based on $\textbf{A}$ccelerated $\textbf{A}$ggregated $\textbf{D}$-Optimal $\textbf{D}$esigns. Our method leverages principled experimental design to improve efficiency and robustness in main effect estimation. We establish theoretical guarantees, including convergence and variance reduction, and validate A2D2E through extensive simulations. We further provide the potential of the proposed method with a case study on real data and applications in language models. The code to reproduce the results can be found at https://github.com/cchihyu/A2D2E.