Stabilizing Test-Time Adaptation of High-Dimensional Simulation Surrogates via D-Optimal Statistics
2026-02-17 • Machine Learning
Machine Learning
AI summaryⓘ
The authors study how machine learning models used to speed up engineering simulations often struggle when tested on new situations different from their training data. They focus on a method called Test-Time Adaptation (TTA) that helps models adjust during deployment, but current TTA techniques don't work well for complex simulation problems. The authors propose a new TTA approach that uses a special way of summarizing important information to make adaptation more stable and reliable. Their method improves performance on challenging simulation tasks with little extra computing effort.
Machine Learning SurrogatesTest-Time AdaptationHigh-Dimensional RegressionDistribution ShiftD-optimal StatisticsSimulation SurrogatesOut-of-Distribution GeneralizationGenerative Design OptimizationSIMSHIFT BenchmarkEngiBench Benchmark
Authors
Anna Zimmel, Paul Setinek, Gianluca Galletti, Johannes Brandstetter, Werner Zellinger
Abstract
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.