AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

The Discrete Gaussian for Differential Privacy

Clément L Canonne, Gautam Kamath, Thomas Steinke

NeurIPS 2020 · Federated learning and privacy › Differential privacy · approach: Local-DP and private estimation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use discrete Gaussian noise instead of rounded continuous GaussianGaussian noise addition for integer data · Tail bound comparison (Figure 2)utility (tail / variance)Improved
Use discrete Gaussian instead of continuous GaussianGaussian mechanism privacy guarantee · (epsilon, delta) curve, large sigma (Figure 1)delta at given epsilonNo clear effect
Use discrete Gaussian instead of continuous GaussianGaussian mechanism privacy guarantee · (epsilon, delta) curve, small sigma (Figure 1)delta at given epsilonHurt
Use the improved concentrated-DP to approximate-DP conversion (Proposition 7) instead of the standard boundDiscrete Gaussian privacy analysis · (epsilon, delta) curve (Figure 1)tightness of delta upper boundImproved
Use discrete Gaussian instead of discrete Laplace noiseAnswering k counting queries under composition · privacy-utility tradeoff, (1, 10^-6)-DP, varying k (Figure 3)variance at fixed privacyImproved
Use discrete Gaussian instead of discrete Laplace noiseAnswering few counting queries · k <= 10 queries (Figure 3 right)variance at fixed privacyHurt
Use discrete Gaussian instead of discrete Laplace noiseAnswering 100 counting queries · minuscule delta (Figure 3 left)achievable (epsilon, delta) at fixed utilityHurt
Compute delta via the closed-form Proposition 7 instead of the exact infimum expressionCDP-to-approximate-DP conversion · parameter regime of interestresulting delta / numerical stabilityNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy