Phase transitions for support recovery under local differential privacy - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Mathematical Statistics and Learning Année : 2023

Phase transitions for support recovery under local differential privacy

Résumé

We address the problem of variable selection in a high-dimensional but sparse mean model, under the additional constraint that only privatized data are available for inference. The original data are vectors with independent entries having a symmetric, strongly log-concave distribution on R. For this purpose, we adopt a recent generalization of classical minimax theory to the framework of local α-differential privacy. We provide lower and upper bounds on the rate of convergence for the expected Hamming loss over classes of at most s-sparse vectors whose non-zero coordinates are separated from 0 by a constant a>0. As corollaries, we derive necessary and sufficient conditions (up to log factors) for exact recovery and for almost full recovery. When we restrict our attention to non-interactive mechanisms that act independently on each coordinate our lower bound shows that, contrary to the non-private setting, both exact and almost full recovery are impossible whatever the value of a in the high-dimensional regime such that nα2/d2≲1. However, in the regime nα2/d2≫log(d) we can exhibit a critical value a∗ (up to a logarithmic factor) such that exact and almost full recovery are possible for all a≫a∗ and impossible for a≤a∗. We show that these results can be improved when allowing for all non-interactive (that act globally on all coordinates) locally α-differentially private mechanisms in the sense that phase transitions occur at lower levels.

Dates et versions

hal-04426748 , version 1 (30-01-2024)

Identifiants

Citer

Cristina Butucea, Amandine Dubois, Adrien Saumard. Phase transitions for support recovery under local differential privacy. Mathematical Statistics and Learning, 2023, 6 (1), pp.1-50. ⟨10.4171/MSL/37⟩. ⟨hal-04426748⟩
15 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More