Research map / Federated learning and privacy / Differential privacy
Differentially Private Bayesian Inference for Exponential Families
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Account for Laplace release noise when inferring the posterior from noisy sufficient statistics | Gibbs sampler · Binomial, multinomial, and exponential models | calibration (Kolmogorov-Smirnov statistic) | Helped |
| Ignore the noise in the released sufficient statistics | Naive method · Binomial, multinomial, and exponential models; moderate n | calibration (Kolmogorov-Smirnov statistic) | Hurt |
| Increase n and ε so privacy noise becomes negligible relative to population size | Naive method · Binomial, multinomial, and exponential models | calibration (Kolmogorov-Smirnov statistic) | Helped |
| Release samples from an over-dispersed privatized posterior | OPS · Binomial model | calibration (Kolmogorov-Smirnov statistic) | Hurt |
| Use noise-aware Gibbs inference instead of the naive method | Private posterior inference · Binomial and multinomial models | MMD to non-private posterior | Helped |
Closest papers by meaning
- On the Differential Privacy of Bayesian Inference (AAAI 2016 · similarity 0.91)
- Differentially Private Statistical Inference through $\beta$-Divergence One Posterior Sampling (NeurIPS 2023 · similarity 0.90)
- Differential Privacy without Sensitivity (NeurIPS 2016 · similarity 0.89)
- Privacy Guarantees in Posterior Sampling under Contamination (NeurIPS 2026 · similarity 0.88)
- On Inherent Privacy of Posterior Sampling: A Unified R\'enyi-Divergence Framework (NeurIPS 2026 · similarity 0.88)
- Private Statistical Estimation via Truncation (NeurIPS 2025 · similarity 0.88)
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.