The Cost of Privacy: Rates of Convergence for Parameter Estimation with Differential Privacy
stat.ML, cs.CR, cs.DS, cs.LG
Submitted: 2019-02-12
Updated: 2026-09-18
Comments: Corrected version; 61 pages, 4 figures, including supplementary material
Project page: https://linjunz.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- CoinPress: Practical Private Mean and Covariance Estimation
- Deep Learning with Gaussian Differential Privacy
- Gaussian Differential Privacy
- Privacy-preserving Prediction
- Concentrated Differential Privacy
- Differentially Private False Discovery Rate Control
- Privately Learning High-Dimensional Distributions
- Finite Sample Differentially Private Confidence Intervals
- Geometrizing rates of convergence under local differential privacy constraints
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
- Online Conformal Prediction for Non-Exchangeable Panel Data
- Deep Time-Series Forecasting in 10 Years: A Survey