Research map / Federated learning and privacy / Differential privacy
Renyi Differential Privacy Mechanisms for Posterior Sampling
Joseph Geumlek, Shuang Song, Kamalika Chaudhuri
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 the concentrated-prior posterior mechanism instead of OPS | Bayesian logistic regression · Abalone, Adult, MNIST 3vs8 | test error | Improved |
| Use the diffuse-likelihood posterior mechanism instead of the concentrated-prior mechanism | Bayesian logistic regression · Abalone, Adult, MNIST 3vs8 | test error | Improved |
| Use direct posterior sampling when its RDP guarantee permits it, rather than the Gaussian mechanism | Beta-Bernoulli sampling · Synthetic data | KL divergence from the true posterior | Improved |
| Use concentrated-posterior sampling rather than diffuse-posterior sampling | Beta-Bernoulli sampling · Synthetic data, lambda = 2 | KL divergence from the true posterior | Mixed |
| Use prior-based posterior mechanisms rather than the Gaussian mechanism | Beta-Bernoulli sampling · Synthetic data, lambda = 15 | KL divergence from the true posterior | Mixed |
| Decrease the data-contribution scale r | Diffuse Posterior · Beta-Bernoulli sampling | RDP epsilon | Improved |
| Decrease the prior scale m, strengthening the prior | Concentrated Posterior · Beta-Bernoulli sampling | RDP epsilon | Improved |
| Use a more informative prior that better matches the population | Beta-Bernoulli prior-based mechanisms · Synthetic data | log likelihood | Improved |
Closest papers by meaning
- On Inherent Privacy of Posterior Sampling: A Unified R\'enyi-Divergence Framework (NeurIPS 2026 · similarity 0.91)
- The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches (NeurIPS 2025 · similarity 0.89)
- Privacy Guarantees in Posterior Sampling under Contamination (NeurIPS 2026 · similarity 0.89)
- Privacy Profiles for Private Selection (ICML 2024 · similarity 0.88)
- Differentially Private Model Merging (NeurIPS 2026 · similarity 0.88)
- 𝑓-Differential Privacy Filters: Validity and Approximate Solutions (NeurIPS 2026 · 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.
