Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping

4 March 2024

Papers citing "Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping"

5 / 5 papers shown

Title
Heavy-Tailed Privacy: The Symmetric alpha-Stable Privacy Mechanism Christopher Zawacki Eyad H. Abed 39 1 0 25 Apr 2025
Understanding the Generalization Error of Markov algorithms through Poissonization Benjamin Dupuis Maxime Haddouche George Deligiannidis Umut Simsekli 42 0 0 11 Feb 2025
Polynomial Time and Private Learning of Unbounded Gaussian Mixture Models Jamil Arbas H. Ashtiani Christopher Liaw 40 23 0 07 Mar 2023
Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent S. H. Lim Yijun Wan Umut cSimcsekli 32 12 0 23 May 2022
Convergence of Langevin Monte Carlo in Chi-Squared and Renyi Divergence Murat A. Erdogdu Rasa Hosseinzadeh Matthew Shunshi Zhang 86 41 0 22 Jul 2020