Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms

Built on

The complexity of differential privacy
Salil Vadhan · 2017
Earlier work this paper cites.
Privacy amplification by iteration
Vitaly Feldman, Ilya Mironov, Kunal Talwar, and Abhradeep Thakurta · 2018
Earlier work this paper cites.
Differential privacy dynamics of langevin diffusion and noisy gradient descent
Rishav Chourasia, Jiayuan Ye, and Reza Shokri · 2021
Earlier work this paper cites.
Numerical composition of differential privacy
Sivakanth Gopi, Yin Tat Lee, and Lukas Wutschitz · 2021
Earlier work this paper cites.

Tight differential privacy for discrete-valued mechanisms and for the subsampled gaussian mechanism using fft
Antti Koskela, Joonas Jälkö, Lukas Prediger, and Antti Honkela · 2021
Cited alongside, same era.
Privacy of noisy stochastic gradient descent: More iterations without more privacy loss
Original
Jason M Altschuler and Kunal Talwar · 2022
Cited alongside, same era.
Connect the dots: Tighter discrete approximations of privacy loss distributions, 2022
Vadym Doroshenko, Badih Ghazi, Pritish Kamath, Ravi Kumar, and Pasin Manurangsi · 2022
Cited alongside, same era.
Google’s differential privacy libraries., 2022
DP Team · 2022
Cited alongside, same era.

Optimal accounting of differential privacy via characteristic function
Yuqing Zhu, Jinshuo Dong, and Yu-Xiang Wang · 2022
Later among the works it cites.
(amplified) banded matrix factorization: A unified approach to private training
Christopher A. Choquette-Choo, Arun Ganesh, Ryan McKenna, Hugh Brendan McMahan, J Keith Rush, Abhradeep Guha Thakurta, and Zheng Xu · 2023
Later among the works it cites.
Privacy amplification for matrix mechanisms, 2023
Christopher A. Choquette-Choo, Arun Ganesh, Thomas Steinke, and Abhradeep Thakurta · 2023
Later among the works it cites.