# Limits of Personalizing Differential Privacy Budgets

arXiv: https://arxiv.org/abs/2605.13503 · HTML: https://mlsanity.com/paper/2605.13503/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 21 of 21)

- [How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy](https://mlsanity.com/paper/2303.00654/) (2023)
- [Individual Privacy Accounting via a Renyi Filter](https://mlsanity.com/paper/2008.11193/) (2020)
- [Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation](https://mlsanity.com/paper/1906.02830/) (2019)
- [Limits of Private Learning with Access to Public Data](https://mlsanity.com/paper/1910.11519/) (2019)
- [Private Estimation with Public Data](https://mlsanity.com/paper/2208.07984/) (2022)
- [Heterogeneous Differential Privacy](https://mlsanity.com/paper/1504.06998/) (2015)
- [Optimal and Differentially Private Data Acquisition: Central and Local Mechanisms](https://mlsanity.com/paper/2201.03968/) (2022)
- [Have it your way: Individualized Privacy Assignment for DP-SGD](https://mlsanity.com/paper/2303.17046/) (2023)
- [Correlated Noise Mechanisms for Differentially Private Learning](https://mlsanity.com/paper/2506.08201/) (2025)
- [Optimal Data Acquisition with Privacy-Aware Agents](https://mlsanity.com/paper/2209.06340/) (2022)
- [Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees](https://mlsanity.com/paper/2202.10517/) (2022)
- [Redrawing the Boundaries on Purchasing Data from Privacy-Sensitive Individuals](https://mlsanity.com/paper/1401.4092/) (2014)
- [Optimal Differentially Private Model Training with Public Data](https://mlsanity.com/paper/2306.15056/) (2023)
- [Individual Sensitivity Preprocessing for Data Privacy](https://mlsanity.com/paper/1804.08645/) (2018)
- [Mean Estimation Under Heterogeneous Privacy: Some Privacy Can Be Free](https://mlsanity.com/paper/2305.09668/) (2023)
- [Mean Estimation Under Heterogeneous Privacy Demands](https://mlsanity.com/paper/2310.13137/) (2023)
- [Oracle-Efficient Differentially Private Learning with Public Data](https://mlsanity.com/paper/2402.09483/) (2024)
- [Public-data Assisted Private Stochastic Optimization: Power and Limitations](https://mlsanity.com/paper/2403.03856/) (2024)
- [Setting varepsilon is not the Issue in Differential Privacy](https://mlsanity.com/paper/2511.06305/) (2025)
- [Managing Correlations in Data and Privacy Demand](https://mlsanity.com/paper/2509.02856/) (2025)
- [Data Sharing with Endogenous Choices over Differential Privacy Levels](https://mlsanity.com/paper/2602.09357/) (2026)

## Abstract (arXiv)

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.