Document Type
Conference Proceeding
Publication Date
2022
Department
Department of Mathematical Sciences
Abstract
We prove that Fp sketch, a well-celebrated streaming algorithm for frequency moments estimation, is differentially private as is when p ∈ (0, 1]. Fp sketch uses only polylogarithmic space, exponentially better than existing DP baselines and only worse than the optimal non-private baseline by a logarithmic factor. The evaluation shows that Fp sketch can achieve reasonable accuracy with differential privacy guarantee. The evaluation code is included in the supplementary material.
Publication Title
ICLR
Recommended Citation
Wang, L.,
Pinelis, I.,
&
Song, D.
(2022).
Differentially Private Fractional Frequency Moments Estimation with Polylogarithmic Space.
ICLR.
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/17215
Creative Commons License
This work is licensed under a
Creative Commons Public Domain Dedication 1.0 License.
Version
Publisher's PDF