A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mahpud, Bar, Sheffet, Or
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915295069732864
author Mahpud, Bar
Sheffet, Or
author_facet Mahpud, Bar
Sheffet, Or
contents We study the problem of differentially private second moment estimation and present a new algorithm that achieve strong privacy-utility trade-offs even for worst-case inputs under subsamplability assumptions on the data. We call an input $(m,α,β)$-subsamplable if a random subsample of size $m$ (or larger) preserves w.p $\geq 1-β$ the spectral structure of the original second moment matrix up to a multiplicative factor of $1\pm α$. Building upon subsamplability, we give a recursive algorithmic framework similar to Kamath et al 2019, that abides zero-Concentrated Differential Privacy (zCDP) while preserving w.h.p. the accuracy of the second moment estimation upto an arbitrary factor of $(1\pmγ)$. We then show how to apply our algorithm to approximate the second moment matrix of a distribution $\mathcal{D}$, even when a noticeable fraction of the input are outliers.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14251
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input
Mahpud, Bar
Sheffet, Or
Machine Learning
Cryptography and Security
Data Structures and Algorithms
We study the problem of differentially private second moment estimation and present a new algorithm that achieve strong privacy-utility trade-offs even for worst-case inputs under subsamplability assumptions on the data. We call an input $(m,α,β)$-subsamplable if a random subsample of size $m$ (or larger) preserves w.p $\geq 1-β$ the spectral structure of the original second moment matrix up to a multiplicative factor of $1\pm α$. Building upon subsamplability, we give a recursive algorithmic framework similar to Kamath et al 2019, that abides zero-Concentrated Differential Privacy (zCDP) while preserving w.h.p. the accuracy of the second moment estimation upto an arbitrary factor of $(1\pmγ)$. We then show how to apply our algorithm to approximate the second moment matrix of a distribution $\mathcal{D}$, even when a noticeable fraction of the input are outliers.
title A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input
topic Machine Learning
Cryptography and Security
Data Structures and Algorithms
url https://arxiv.org/abs/2505.14251