English

Differentially Private Linear Regression over Fully Decentralized Datasets

Cryptography and Security 2020-04-17 v1 Machine Learning

Abstract

This paper presents a differentially private algorithm for linear regression learning in a decentralized fashion. Under this algorithm, privacy budget is theoretically derived, in addition to that the solution error is shown to be bounded by O(t)O(t) for O(1/t)O(1/t) descent step size and O(exp(t1e))O(\exp(t^{1-e})) for O(te)O(t^{-e}) descent step size.

Keywords

Cite

@article{arxiv.2004.07425,
  title  = {Differentially Private Linear Regression over Fully Decentralized Datasets},
  author = {Yang Liu and Xiong Zhang and Shuqi Qin and Xiaoping Lei},
  journal= {arXiv preprint arXiv:2004.07425},
  year   = {2020}
}

Comments

FL-NeurIPS'19

R2 v1 2026-06-23T14:53:11.702Z