Skip to yearly menu bar Skip to main content


Distribution Learnability and Robustness

Shai Ben-David · Alex Bie · Gautam Kamath · Tosca Lechner

Great Hall & Hall B1+B2 (level 1) #1725
[ ]
Wed 13 Dec 8:45 a.m. PST — 10:45 a.m. PST


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.

Chat is not available.