Differentially private high dimensional sparse covariance matrix estimation

Di Wang, Jinhui Xu

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


In this paper, we study the problem of estimating the covariance matrix under differential privacy, where the underlying covariance matrix is assumed to be sparse and of high dimensions. We propose a new method, called DP-Thresholding, to achieve a non-trivial ℓ2-norm based error bound whose dependence on the dimension drops to logarithmic instead of polynomial, it is significantly better than the existing ones, which add noise directly to the empirical covariance matrix. We also extend the ℓ2-norm based error bound to a general ℓw-norm based one for any 1≤w≤∞, and show that they share the same upper bound asymptotically. Our approach can be easily extended to local differential privacy. Experiments on the synthetic datasets show results that are consistent with theoretical claims.
Original languageEnglish (US)
JournalTheoretical Computer Science
StatePublished - Mar 10 2021

Bibliographical note

KAUST Repository Item: Exported on 2021-03-25
Acknowledgements: This research was supported in part by the National Science Foundation (NSF) through grants CCF-1422324 and CCF-1716400.

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science


Dive into the research topics of 'Differentially private high dimensional sparse covariance matrix estimation'. Together they form a unique fingerprint.

Cite this