Private Learning of Littlestone Classes, Revisited

We consider online and PAC learning of Littlestone classes subject to the constraint of approximate differential privacy. Our main result is a private learner to online-learn a Littlestone class with a mistake bound of tildeO(d9.5· log(T)) in the realizable case, where d denotes the Littlestone dimension and T the time horizon. This is a doubly-exponential improvement over the state-of-the-art [GL'21] and comes polynomially close to the lower bound for this task. The advancement is made possible by a couple of ingredients. The first is a clean and refined interpretation of the ``irreducibility'' technique from the state-of-the-art private PAC-learner for Littlestone classes [GGKM'21]. Our new perspective also allows us to improve the PAC-learner of [GGKM'21] and give a sample complexity upper bound of widetildeO(fracd5 log(1/δβ)varepsilon α) where α and β denote the accuracy and confidence of the PAC learner, respectively. This improves over [GGKM'21] by factors of fracdα and attains an optimal dependence on α. Our algorithm uses a private sparse selection algorithm to sample from a pool of strongly input-dependent candidates. However, unlike most previous uses of sparse selection algorithms, where one only cares about the utility of output, our algorithm requires understanding and manipulating the actual distribution from which an output is drawn. In the proof, we use a sparse version of the Exponential Mechanism from [GKM'21] which behaves nicely under our framework and is amenable to a very easy utility proof.