Research map / Federated learning and privacy / Differential privacy
Gaussian Differential Privacy on Riemannian Manifolds
Yangdi Jiang, Xiaotian Chang, Yi Liu, Lei Ding, Linglong Kong, Bei Jiang
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 Riemannian Gaussian noise instead of Riemannian Laplace noise to achieve mu-GDP on the sphere | private Frechet mean on S^2 · S^2 simulation, n=10, sigma=k/4 | Riemannian distance to non-private mean | Improved |
| Increase the privacy budget mu (less noise) | Gaussian vs Laplace mechanism · S^2 simulation | utility gap | Mixed |
Closest papers by meaning
- Differential Privacy Over Riemannian Manifolds (NeurIPS 2021 · similarity 0.93)
- Exponential-Wrapped Mechanisms: Differential Privacy on Hadamard Manifolds Made Practical (ICLR 2026 · similarity 0.90)
- Differentially Private Geodesic Regression (ICML 2026 · similarity 0.88)
- Intrinsic Riemannian Cross-covariance for Manifold-valued Random Objects (NeurIPS 2026 · similarity 0.85)
- Riemannian Proximal Sampler for High-accuracy Sampling on Manifolds (NeurIPS 2025 · similarity 0.84)
- Wrapped Gaussian on the manifold of Symmetric Positive Definite Matrices (ICML 2025 · similarity 0.84)
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.
