On the Statistical Complexity of Estimation and Testing under Privacy Constraints - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Transactions on Machine Learning Research Journal Année : 2023

On the Statistical Complexity of Estimation and Testing under Privacy Constraints

Résumé

The challenge of producing accurate statistics while respecting the privacy of the individuals in a sample is an important area of research. We study minimax lower bounds for classes of differentially private estimators. In particular, we show how to characterize the power of a statistical test under differential privacy in a plug-and-play fashion by solving an appropriate transport problem. With specific coupling constructions, this observation allows us to derive Le Cam-type and Fano-type inequalities not only for regular definitions of differential privacy but also for those based on Renyi divergence. We then proceed to illustrate our results on three simple, fully worked out examples. In particular, we show that the problem class has a huge importance on the provable degradation of utility due to privacy. In certain scenarios, we show that maintaining privacy results in a noticeable reduction in performance only when the level of privacy protection is very high. Conversely, for other problems, even a modest level of privacy protection can lead to a significant decrease in performance. Finally, we demonstrate that the DP-SGLD algorithm, a private convex solver, can be employed for maximum likelihood estimation with a high degree of confidence, as it provides near-optimal results with respect to both the size of the sample and the level of privacy protection. This algorithm is applicable to a broad range of parametric estimation procedures, including exponential families.
Fichier principal
Vignette du fichier
tmlr_final.pdf (501.88 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03794374 , version 1 (03-10-2022)
hal-03794374 , version 2 (28-04-2023)
hal-03794374 , version 3 (22-12-2023)

Identifiants

  • HAL Id : hal-03794374 , version 2

Citer

Clément Lalanne, Aurélien Garivier, Rémi Gribonval. On the Statistical Complexity of Estimation and Testing under Privacy Constraints. Transactions on Machine Learning Research Journal, 2023. ⟨hal-03794374v2⟩
109 Consultations
179 Téléchargements

Partager

Gmail Facebook X LinkedIn More