Free Gap Estimates from the Exponential Mechanism, Sparse Vector, Noisy Max and Related Algorithms
This work provides a method to improve the accuracy of differentially private counting queries for users of private selection algorithms, representing an incremental advancement in privacy-preserving data analysis.
This paper demonstrates that private selection algorithms like the Exponential Mechanism, Noisy Max, and Sparse Vector can release information about the gaps between selected and other candidate items without additional privacy cost. This 'free gap information' can improve the accuracy of subsequent counting queries by up to 66%.
Private selection algorithms, such as the Exponential Mechanism, Noisy Max and Sparse Vector, are used to select items (such as queries with large answers) from a set of candidates, while controlling privacy leakage in the underlying data. Such algorithms serve as building blocks for more complex differentially private algorithms. In this paper we show that these algorithms can release additional information related to the gaps between the selected items and the other candidates for free (i.e., at no additional privacy cost). This free gap information can improve the accuracy of certain follow-up counting queries by up to 66%. We obtain these results from a careful privacy analysis of these algorithms. Based on this analysis, we further propose novel hybrid algorithms that can dynamically save additional privacy budget.