arXiv:2604.20761v1 Announce Type: new Abstract: In this paper, we develop a novel privacy mechanism for Riemannian manifold-valued data. Our key contribution lies in uncovering unexpected connections among geometric analysis, heat diffusion models, and differential privacy (DP). We characterize the Renyi divergence via dimension-free Harnack inequalities on Riemannian manifolds and establish Renyi
Geometric Renyi Differential Privacy: Ricci Curvature Characterized by Heat Diffusion Mechanisms
Xiaotian Chang, Yangdi Jiang, Cyrus Mostajeran, Qirui Hu·arXiv stat.ML··1 min read
a
Continue reading on arXiv stat.ML
This article was sourced from arXiv stat.ML's RSS feed. Visit the original for the complete story.