Actually, All Learnable Distribution Classes Are Privately Learnable
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 ($\varepsilon, \delta$)-differential privacy up to arbitrarily small target error with finitely many samples.
By Mohammad Afzali, Hassan Ashtiani, Alex Bie, Gautam Kamath, Peihan Liu, Argyris Mouzakis, Vikrant SinghalarXiv cs.LG
Read the full story
Originally published by arXiv cs.LG on Oct 22, 2026.
Comments
Sign in to join the discussion.