Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation

We provide an improved analysis of standard differentially private gradient descent for linear regression under the squared error loss. Under modest assumptions on the input, we characterize the distribution of the iterate at each time step. Our analysis leads to new results on the algorithm's...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Brown, Gavin, Krishnamurthy Dvijotham, Evans, Georgina, Liu, Daogao, Smith, Adam, Thakurta, Abhradeep
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 21.02.2024
Subjects
Algorithms
Confidence intervals
Empirical analysis
Statistical analysis
Synthetic data
Online AccessGet full text

Cover

More Information
Summary:We provide an improved analysis of standard differentially private gradient descent for linear regression under the squared error loss. Under modest assumptions on the input, we characterize the distribution of the iterate at each time step. Our analysis leads to new results on the algorithm's accuracy: for a proper fixed choice of hyperparameters, the sample complexity depends only linearly on the dimension of the data. This matches the dimension-dependence of the (non-private) ordinary least squares estimator as well as that of recent private algorithms that rely on sophisticated adaptive gradient-clipping schemes (Varshney et al., 2022; Liu et al., 2023). Our analysis of the iterates' distribution also allows us to construct confidence intervals for the empirical optimizer which adapt automatically to the variance of the algorithm on a particular data set. We validate our theorems through experiments on synthetic data.
ISSN:2331-8422