Skip to Main content Skip to Navigation
Conference papers

Private Protocols for U-Statistics in the Local Model and Beyond

James Bell 1 Aurélien Bellet 2 Adrià Gascón 3 Tejas Kulkarni 4
2 MAGNET - Machine Learning in Information Networks
CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189, Inria Lille - Nord Europe
Abstract : In this paper, we study the problem of computing $U$-statistics of degree $2$, i.e., quantities that come in the form of averages over pairs of data points, in the local model of differential privacy (LDP). The class of $U$-statistics covers many statistical estimates of interest, including Gini mean difference, Kendall's tau coefficient and Area under the ROC Curve (AUC), as well as empirical risk measures for machine learning problems such as ranking, clustering and metric learning. We first introduce an LDP protocol based on quantizing the data into bins and applying randomized response, which guarantees an $\epsilon$-LDP estimate with a Mean Squared Error (MSE) of $O(1/\sqrt{n}\epsilon)$ under regularity assumptions on the $U$-statistic or the data distribution. We then propose a specialized protocol for AUC based on a novel use of hierarchical histograms that achieves MSE of $O(\alpha^3/n\epsilon^2)$ for arbitrary data distribution. We also show that 2-party secure computation allows to design a protocol with MSE of $O(1/n\epsilon^2)$, without any assumption on the kernel function or data distribution and with total communication linear in the number of users $n$. Finally, we evaluate the performance of our protocols through experiments on synthetic and real datasets.
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download
Contributor : Aurélien Bellet <>
Submitted on : Monday, May 4, 2020 - 11:17:35 AM
Last modification on : Tuesday, May 5, 2020 - 1:34:26 AM


  • HAL Id : hal-02310236, version 2
  • ARXIV : 1910.03861


James Bell, Aurélien Bellet, Adrià Gascón, Tejas Kulkarni. Private Protocols for U-Statistics in the Local Model and Beyond. International Conference on Artificial Intelligence and Statistics (AISTATS 2020), 2020, Palermo, Italy. ⟨hal-02310236v2⟩



Record views


Files downloads