Research map / Federated learning and privacy / Differential privacy
The Discrete Gaussian for Differential Privacy
Clément L Canonne, Gautam Kamath, Thomas Steinke
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use discrete Gaussian noise instead of rounded continuous Gaussian | Gaussian noise addition for integer data · Tail bound comparison (Figure 2) | utility (tail / variance) | Improved |
| Use discrete Gaussian instead of continuous Gaussian | Gaussian mechanism privacy guarantee · (epsilon, delta) curve, large sigma (Figure 1) | delta at given epsilon | No clear effect |
| Use discrete Gaussian instead of continuous Gaussian | Gaussian mechanism privacy guarantee · (epsilon, delta) curve, small sigma (Figure 1) | delta at given epsilon | Hurt |
| Use the improved concentrated-DP to approximate-DP conversion (Proposition 7) instead of the standard bound | Discrete Gaussian privacy analysis · (epsilon, delta) curve (Figure 1) | tightness of delta upper bound | Improved |
| Use discrete Gaussian instead of discrete Laplace noise | Answering k counting queries under composition · privacy-utility tradeoff, (1, 10^-6)-DP, varying k (Figure 3) | variance at fixed privacy | Improved |
| Use discrete Gaussian instead of discrete Laplace noise | Answering few counting queries · k <= 10 queries (Figure 3 right) | variance at fixed privacy | Hurt |
| Use discrete Gaussian instead of discrete Laplace noise | Answering 100 counting queries · minuscule delta (Figure 3 left) | achievable (epsilon, delta) at fixed utility | Hurt |
| Compute delta via the closed-form Proposition 7 instead of the exact infimum expression | CDP-to-approximate-DP conversion · parameter regime of interest | resulting delta / numerical stability | No clear effect |
Closest papers by meaning
- Privacy Guarantees in Posterior Sampling under Contamination (NeurIPS 2026 · similarity 0.86)
- Privacy amplification by random allocation (NeurIPS 2025 · similarity 0.85)
- Optimizing Noise Distributions for Differential Privacy (ICML 2025 · similarity 0.85)
- The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches (NeurIPS 2025 · similarity 0.84)
- Differentially Private Equivalence Testing for Continuous Distributions and Applications (NeurIPS 2024 · similarity 0.83)
- Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy (ICLR 2024 · similarity 0.83)
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.
