Paperlane

no. 16 · Tuesday 17 November 2026

Ensembles of Random Partition-Based Models under Covariate Shift

Mary Versa Clemens-Sewall and Eliza O'Reilly

math.ST · v2 · 29 pp

Abstract

Distribution shifts, including covariate shifts, are ubiquitous in real-world applications of machine learning. Empirical evidence suggests that, across a variety of models with and without downstream adaptation, ensembles tend to be more robust to covariate shift than single models. We extend the theory of covariate shift severity from single models to ensembles, providing theoretical justification for the empirical trends. We introduce new discrepancy measures of covariate shift severity to control the risk of partition-based kernel estimators. We then show that with sufficient ensemble size, these models can achieve minimax-optimal risk convergence rates under covariate shift. Our results suggest that modelers can expect to need larger ensemble sizes for more severe covariate shifts.

comments
29 pages, 3 figures
fields
Statistics Theory
pdf ↗ page arXiv:2611.05195 ↗