The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lev, Omri, Srinivasan, Vishwak, Shenfeld, Moshe, Ligett, Katrina, Sekhari, Ayush, Wilson, Ashia C.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909636491214848
author Lev, Omri
Srinivasan, Vishwak
Shenfeld, Moshe
Ligett, Katrina
Sekhari, Ayush
Wilson, Ashia C.
author_facet Lev, Omri
Srinivasan, Vishwak
Shenfeld, Moshe
Ligett, Katrina
Sekhari, Ayush
Wilson, Ashia C.
contents Gaussian sketching, which consists of pre-multiplying the data with a random Gaussian matrix, is a widely used technique for multiple problems in data science and machine learning, with applications spanning computationally efficient optimization, coded computing, and federated learning. This operation also provides differential privacy guarantees due to its inherent randomness. In this work, we revisit this operation through the lens of Renyi Differential Privacy (RDP), providing a refined privacy analysis that yields significantly tighter bounds than prior results. We then demonstrate how this improved analysis leads to performance improvement in different linear regression settings, establishing theoretical utility guarantees. Empirically, our methods improve performance across multiple datasets and, in several cases, reduce runtime.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24603
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches
Lev, Omri
Srinivasan, Vishwak
Shenfeld, Moshe
Ligett, Katrina
Sekhari, Ayush
Wilson, Ashia C.
Machine Learning
Gaussian sketching, which consists of pre-multiplying the data with a random Gaussian matrix, is a widely used technique for multiple problems in data science and machine learning, with applications spanning computationally efficient optimization, coded computing, and federated learning. This operation also provides differential privacy guarantees due to its inherent randomness. In this work, we revisit this operation through the lens of Renyi Differential Privacy (RDP), providing a refined privacy analysis that yields significantly tighter bounds than prior results. We then demonstrate how this improved analysis leads to performance improvement in different linear regression settings, establishing theoretical utility guarantees. Empirically, our methods improve performance across multiple datasets and, in several cases, reduce runtime.
title The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches
topic Machine Learning
url https://arxiv.org/abs/2505.24603