5 papers
Actually, All Learnable Distribution Classes Are Privately Learnable
Mohammad Afzali, Hassan Ashtiani, Alex Bie +4
We show that every class of distributions that is learnable up to arbitrarily small target error in total variation distance with finitely many samples is also learnable under ($\v…
ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?
Peihan Liu, Lucas Rosenblatt, Weiwei Kong +7
Differentially private (DP) text synthesis promises to unlock sensitive corpora for model training, but it remains unclear whether DP synthetic data transmits genuinely new knowled…
Near-Optimal Machine Unlearning Utility for Smooth Strongly Convex Losses
Matthew Regehr, Gautam Kamath, Andrew Lowy
Machine unlearning is motivated by legal and user-facing requirements to remove the influence of individuals' data from trained models, such as the right to be forgotten. Prior wor…
On the Learnability of Distribution Classes with Adaptive Adversaries
Tosca Lechner, Alex Bie, Gautam Kamath
We consider the question of learnability of distribution classes in the presence of adaptive adversaries -- that is, adversaries capable of intercepting the samples requested by a…
Distribution Learnability and Robustness
Shai Ben-David, Alex Bie, Gautam Kamath +1
We examine the relationship between learnability and robust (or agnostic) learnability for the problem of distribution learning. We show that, contrary to other learning settings (…