Private Data Stream Analysis for Universal Symmetric Norm Estimation

Vladimir Braverman, Joel Manning, Steven Wu, Samson Zhou

Keywords: differential privacy, norm estimation

TL;DR: We provide a differentially private algorithm that approximate an arbitrary number of symmetric norms on a data stream

Abstract: We study how to release summary statistics on a data stream subject to the constraint of differential privacy. In particular, we focus on releasing the family of \emph{symmetric norms}, which are invariant under sign-flips and coordinate-wise permutations on an input data stream and include $L_p$ norms, $k$-support norms, top-$k$ norms, and the box norm as special cases. Although it may be possible to design and analyze a separate mechanism for each symmetric norm, we propose a general parametrizable framework that differentially privately releases a number of sufficient statistics from which the approximation of all symmetric norms can be simultaneously computed. Our framework partitions the coordinates of the underlying frequency vector into different levels based on their magnitude and releases approximate frequencies for the ``heavy'' coordinates in important levels and releases approximate level sizes for the ``light'' coordinates in important levels. Surprisingly, our mechanism allows for the release of an \emph{arbitrary} number of symmetric norm approximations without any overhead or additional loss in privacy. Moreover, our mechanism permits $(1+\alpha)$-approximation to each of the symmetric norms and can be implemented using sublinear space in the streaming model for many regimes of the accuracy and privacy parameters.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)