Publications · Preprint · arXiv 2025
Rényi differential privacy for heavy-tailed SDEs via fractional Poincaré inequalities
arXiv preprint, 2025.
In brief
Injecting heavy-tailed rather than Gaussian noise into gradient-based training changes its privacy properties. Working with the heavy-tailed stochastic differential equations that describe such algorithms in continuous time, the paper derives Rényi differential-privacy guarantees through fractional Poincaré inequalities, extending privacy analysis beyond the Gaussian mechanism.
Cite
@misc{dupuis2025renyi,
title = {Rényi differential privacy for heavy-tailed SDEs via fractional Poincaré inequalities},
author = {Benjamin Dupuis and Mert Gürbüzbalaban and Umut Şimşekli and Jian Wang and Sinan Yıldırım and Lingjiong Zhu},
year = {2025},
howpublished = {arXiv preprint arXiv:2511.15634},
}Relatedsame topics