Differential Privacy Guarantees for Stochastic Gradient Langevin Dynamics

28 January 2022

Papers citing "Differential Privacy Guarantees for Stochastic Gradient Langevin Dynamics"

8 / 8 papers shown

Title
An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses Hao Liang W. Zhang Xinlei He Kaishun He Hong Xing 47 0 0 25 Feb 2025
Understanding the Generalization Error of Markov algorithms through Poissonization Benjamin Dupuis Maxime Haddouche George Deligiannidis Umut Simsekli 47 0 0 11 Feb 2025
Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping Umut Simsekli Mert Gurbuzbalaban S. Yıldırım Lingjiong Zhu 38 2 0 04 Mar 2024
Privacy Loss of Noisy Stochastic Gradient Descent Might Converge Even for Non-Convex Losses S. Asoodeh Mario Díaz 20 6 0 17 May 2023
Resolving the Mixing Time of the Langevin Algorithm to its Stationary Distribution for Log-Concave Sampling Jason M. Altschuler Kunal Talwar 38 24 0 16 Oct 2022
On the Statistical Complexity of Estimation and Testing under Privacy Constraints Clément Lalanne Aurélien Garivier Rémi Gribonval 27 7 0 05 Oct 2022
Differentially Private Learning Needs Hidden State (Or Much Faster Convergence) Jiayuan Ye Reza Shokri FedML 27 44 0 10 Mar 2022
Opacus: User-Friendly Differential Privacy Library in PyTorch Ashkan Yousefpour I. Shilov Alexandre Sablayrolles Davide Testuggine Karthik Prasad ... Sayan Gosh Akash Bharadwaj Jessica Zhao Graham Cormode Ilya Mironov VLM 168 350 0 25 Sep 2021