AI RESEARCH
Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift
arXiv CS.LG
•
ArXi:2605.07005v1 Announce Type: cross Recent work on provably efficient algorithms for learning with distribution shift has focused on two models: PQ learning (Goldwasser ) and TDS learning (Klivans ). Algorithms for TDS learning are allowed to reject a test set entirely if distribution shift is detected. In contrast, PQ learners may only reject points that are deemed out-of-distribution on an individual basis. Our main result is a surprising equivalence between these two models in the distribution-free setting.