An Equivalence Between Private Classification and Online Prediction
FOCS, pp. 389-402, 2020.
We prove that every concept class with finite Littlestone dimension can be learned by an (approximate) differentially-private algorithm. This answers an open question of Alon et al. (STOC 2019) who proved the converse statement (this question was also asked by Neel et al.~(FOCS 2019)). Together these two results yield an equivalence bet...More
PPT (Upload PPT)