English

Near Optimal Private and Robust Linear Regression

Machine Learning 2023-02-01 v1 Cryptography and Security Statistics Theory Machine Learning Statistics Theory

Abstract

We study the canonical statistical estimation problem of linear regression from nn i.i.d.~examples under (ε,δ)(\varepsilon,\delta)-differential privacy when some response variables are adversarially corrupted. We propose a variant of the popular differentially private stochastic gradient descent (DP-SGD) algorithm with two innovations: a full-batch gradient descent to improve sample complexity and a novel adaptive clipping to guarantee robustness. When there is no adversarial corruption, this algorithm improves upon the existing state-of-the-art approach and achieves a near optimal sample complexity. Under label-corruption, this is the first efficient linear regression algorithm to guarantee both (ε,δ)(\varepsilon,\delta)-DP and robustness. Synthetic experiments confirm the superiority of our approach.

Keywords

Cite

@article{arxiv.2301.13273,
  title  = {Near Optimal Private and Robust Linear Regression},
  author = {Xiyang Liu and Prateek Jain and Weihao Kong and Sewoong Oh and Arun Sai Suggala},
  journal= {arXiv preprint arXiv:2301.13273},
  year   = {2023}
}
R2 v1 2026-06-28T08:27:26.572Z