Part of Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Main Conference Track
Shai Ben-David, Alex Bie, Gautam Kamath, Tosca Lechner
We examine the relationship between learnability and robust learnability for the problem of distribution learning.We show that learnability implies robust learnability if the adversary can only perform additive contamination (and consequently, under Huber contamination), but not if the adversary is allowed to perform subtractive contamination. Thus, contrary to other learning settings (e.g., PAC learning of function classes), realizable learnability does not imply agnostic learnability. We also explore related implications in the context of compression schemes and differentially private learnability.