Locally differentially private frequency distribution estimation with relative error optimization

Ning Wang, Yifei Liu, Zhigang Wang, Zhiqiang Wei, Ruichun Tang, Peng Tang, Ge Yu

Abstract: In this paper, an iterative framework iterUA is designed for publishing frequency distribution with reduced relative error on multidimensional data under LDP. In each iteration step, the optimized user allocation strategy OUAS is invoked to reduce the relative error in the derived results. In the furture, we are going to investigate the problem of the relative error optimization for mean estimation under LDP.