PLAN: Variance-Aware Private Mean Estimation

arXiv:2306.08745v3 Announce Type: replace-cross
Abstract: Differentially private mean estimation is an important building block in privacy-preserving algorithms for data analysis and machine learning. Though the trade-off between privacy and utility is well understood in the worst case, many datasets exhibit structure that could potentially be exploited to yield better algorithms. In this paper we present $\textit{Private Limit Adapted Noise}$ (PLAN), a family of differentially private algorithms for mean estimation in the setting where inputs are independently sampled from a distribution …

abstract algorithms analysis arxiv block building case cs.cr cs.ds cs.lg data data analysis datasets machine machine learning mean paper privacy trade trade-off type utility variance