Oracle-Efficient Differentially Private Learning with Public Data

arXiv:2402.09483v1 Announce Type: cross
Abstract: Due to statistical lower bounds on the learnability of many function classes under privacy constraints, there has been recent interest in leveraging public data to improve the performance of private learning algorithms. In this model, algorithms must always guarantee differential privacy with respect to the private samples while also ensuring learning guarantees when the private data distribution is sufficiently close to that of the public data. Previous work has demonstrated that when sufficient public, unlabelled …

algorithms arxiv constraints cs.cr cs.lg data differential privacy function guarantee interest oracle performance privacy private public respect stat.ml under