Abstract:A key technical difficulty in differential privacy is selecting a privacy budget that satisfies privacy requirements while maximizing utility. A natural and well-studied workaround is to use personalized privacy budgets, which may differ across agents. In this paper, we show that personalized budgets come with major limitations and that for mean estimation, the dominant factor is not full personalization, but rather choosing the right effective privacy budget. This can be achieved through a simple thresholding operator that we describe. Compared with this thresholding baseline, the gains obtained by fully personalized mechanisms are limited. In particular, we precisely quantify the constant-factor improvement in settings with mixed private and public datasets and in private datasets with two levels of privacy requirements. We also establish upper bounds and identify regimes of maximal gain for arbitrary privacy requirements.
| Subjects: | Cryptography and Security (cs.CR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.13503 [cs.CR] |
| (or arXiv:2605.13503v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2605.13503 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Edwige Cyffers [view email]
[v1]
Wed, 13 May 2026 13:24:50 UTC (2,581 KB)