About the Cost of Central Privacy in Density Estimation - Archive ouverte HAL Access content directly
Journal Articles Transactions on Machine Learning Research Journal Year : 2023

About the Cost of Central Privacy in Density Estimation


We study non-parametric density estimation for densities in Lipschitz and Sobolev spaces, and under central privacy. In particular, we investigate regimes where the privacy budget is not supposed to be constant. We consider the classical definition of central differential privacy, but also the more recent notion of central concentrated differential privacy. We recover the result of Barber & Duchi (2014) stating that histogram estimators are optimal against Lipschitz distributions for the L2 risk, and under regular differential privacy, and we extend it to other norms and notions of privacy. Then, we investigate higher degrees of smoothness, drawing two conclusions: First, and contrary to what happens with constant privacy budget (Wasserman & Zhou, 2010), there are regimes where imposing privacy degrades the regular minimax risk of estimation on Sobolev densities. Second, so-called projection estimators are near-optimal against the same classes of densities in this new setup with pure differential privacy, but contrary to the constant privacy budget case, it comes at the cost of relaxation. With zero concentrated differential privacy, there is no need for relaxation, and we prove that the estimation is optimal.
Fichier principal
Vignette du fichier
preprint.pdf (443.14 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04133655 , version 1 (22-06-2023)
hal-04133655 , version 2 (21-09-2023)
hal-04133655 , version 3 (22-12-2023)



Clément Lalanne, Aurélien Garivier, Rémi Gribonval. About the Cost of Central Privacy in Density Estimation. Transactions on Machine Learning Research Journal, 2023. ⟨hal-04133655v2⟩
53 View
88 Download



Gmail Facebook X LinkedIn More