Year: 2026
Type: article
Abstract: The performance of machine learning models degrades when the training population is different from that seen under operation. Toward assessing distributional robustness, we study the worst-case performance of a model over all subpopulations of a given size defined with respect to core attributes Z. This notion of robustness can consider arbitrary (continuous) attributes Z and automatically accounts for complex intersectionality in disadvantaged groups. We develop a scalable yet principled two-stage estimation procedure that can evaluate the robustness of state-of-the-art models. We prove that our procedure enjoys several finite-sample convergence guarantees, including dimension-free convergence. Instead of overly conservative notions based on Rademacher complexities, our evaluation error depends on the dimension of Z only through the out-of-sample error in estimating the performance conditional on Z. On real data sets, we demonstrate that our method certifies the robustness of a model and prevents deployment of unreliable models.
Authors: Mike Li, Daksh Mittal, Hongseok Namkoong, Shangzhou Xia
Institution: Columbia University
Language: English
Subfield: Safety Research
Field: Social Sciences
Domain: Social Sciences
SDG: Reduced inequalities
Open Access status: green
OpenAlex ID: W3212519405