Research map / Federated learning and privacy / Differential privacy
Privacy-Aware Rejection Sampling
Jordan Awan, Vinayak Rao
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 |
|---|---|---|---|
| lower R from 2 to 1.1 (acceptance probabilities closer across neighboring databases) (ablation) | simple rejection sampler · runtime privacy cost, delta=0.001 | epsilon(delta): 5.52 -> .356 | Improved |
| lower delta from 0.1 to 10^{-6} at R=2 (ablation) | simple rejection sampler · runtime privacy cost | epsilon(delta): .916 -> 12.43 | Hurt |
| use equally spaced grid points when refining the piecewise-linear approximation | adaptive rejection sampler for log-Holder densities · 7-Lipschitz example | approximation radius r-hat | Improved |
Closest papers by meaning
- Purifying Approximate Differential Privacy with Randomized Post-processing (NeurIPS 2025 · similarity 0.89)
- How Private are DP-SGD Implementations? (ICML 2024 · similarity 0.88)
- 𝑓-Differential Privacy Filters: Validity and Approximate Solutions (NeurIPS 2026 · similarity 0.88)
- Optimal Survey Design for Private Mean Estimation (ICML 2025 · similarity 0.88)
- Privacy Guarantees in Posterior Sampling under Contamination (NeurIPS 2026 · similarity 0.87)
- Auditing $f$-differential privacy in one run (ICML 2025 · similarity 0.87)
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.
