ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2012.03817
21
22

A bounded-noise mechanism for differential privacy

7 December 2020
Y. Dagan
Gil Kur
ArXivPDFHTML
Abstract

We present an asymptotically optimal (ϵ,δ)(\epsilon,\delta)(ϵ,δ) differentially private mechanism for answering multiple, adaptively asked, Δ\DeltaΔ-sensitive queries, settling the conjecture of Steinke and Ullman [2020]. Our algorithm has a significant advantage that it adds independent bounded noise to each query, thus providing an absolute error bound. Additionally, we apply our algorithm in adaptive data analysis, obtaining an improved guarantee for answering multiple queries regarding some underlying distribution using a finite sample. Numerical computations show that the bounded-noise mechanism outperforms the Gaussian mechanism in many standard settings.

View on arXiv
Comments on this paper