English

Statistical Inference for Differentially Private Stochastic Gradient Descent

Machine Learning 2025-12-15 v2 Machine Learning Methodology

Abstract

Privacy preservation in machine learning, particularly through Differentially Private Stochastic Gradient Descent (DP-SGD), is critical for sensitive data analysis. However, existing statistical inference methods for SGD predominantly focus on cyclic subsampling, while DP-SGD requires randomized subsampling. This paper first bridges this gap by establishing the asymptotic properties of SGD under the randomized rule and extending these results to DP-SGD. For the output of DP-SGD, we show that the asymptotic variance decomposes into statistical, sampling, and privacy-induced components. Two methods are proposed for constructing valid confidence intervals: the plug-in method and the random scaling method. We also perform extensive numerical analysis, which shows that the proposed confidence intervals achieve nominal coverage rates while maintaining privacy.

Keywords

Cite

@article{arxiv.2507.20560,
  title  = {Statistical Inference for Differentially Private Stochastic Gradient Descent},
  author = {Xintao Xia and Linjun Zhang and Zhanrui Cai},
  journal= {arXiv preprint arXiv:2507.20560},
  year   = {2025}
}
R2 v1 2026-07-01T04:21:36.212Z