Rank-Constrained Adaptation for Reliable Real-World Performance

Excerpt

arXiv:2602.06924v3 Announce Type: replace Abstract: Deep learning models trained to optimize average accuracy often exhibit systematic failures on particular subpopulations. In real-world settings like healthcare, the subpopulations most affected by such disparities are frequently unlabeled, partially observed, or not known in advance. Existing group-robust methods typically assume prior knowledge of the relevant subgroups, using group annotations for training, validation, or model selection. We