Machine learning surrogates are increasingly used in engineering to accelerate costly simulations, yet distribution shifts between training and deployment often cause severe performance degradation (e.g., unseen geometries or configurations). Test-Time Adaptation (TTA) can mitigate such shifts, but existing methods are largely developed for lower-dimensional classification with structured outputs and visually aligned input-output relationships, making them unstable for the high-dimensional, unstructured and regression problems common in simulation. We address this challenge by proposing a TTA framework based on storing maximally informative (D-optimal) statistics, which jointly enables stable adaptation and principled parameter selection at test time. When applied to pretrained simulation surrogates, our method yields up to 7% out-of-distribution improvements at negligible computational cost. To the best of our knowledge, this is the first systematic demonstration of effective TTA for high-dimensional simulation regression and generative design optimization, validated on the SIMSHIFT and EngiBench benchmarks.

翻译：机器学习代理模型在工程领域中正日益被用于加速昂贵的仿真计算，然而训练与部署之间的分布偏移常导致严重的性能退化（例如未见过的几何构型或配置参数）。测试时自适应方法能够缓解此类偏移，但现有方法主要针对具有结构化输出和视觉对齐输入输出关系的低维分类问题而设计，对于仿真中常见的高维、非结构化回归问题往往表现不稳定。我们通过提出一种基于存储最大化信息量（D最优）统计量的测试时自适应框架来解决这一挑战，该框架能够同时实现稳定的自适应和测试时的原则性参数选择。当应用于预训练的仿真代理模型时，本方法以可忽略的计算成本实现了最高7%的分布外性能提升。据我们所知，这是在SIMSHIFT和EngiBench基准上验证的首个针对高维仿真回归与生成式设计优化问题的系统性有效测试时自适应方法演示。