Improving Differentially Private SGD via Randomly Sparsified Gradients

Improving Differentially Private SGD via Randomly Sparsified Gradients

1 December 2021

Matthew B. Blaschko

Papers citing "Improving Differentially Private SGD via Randomly Sparsified Gradients"

7 / 7 papers shown

Title
Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails Haichao Sha Yang Cao Yong Liu Yuncheng Wu Ruixuan Liu Hong Chen 35 2 0 27 May 2024
TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data Richeng Jin Yujie Gu Kai Yue Xiaofan He Zhaoyang Zhang Huaiyu Dai FedML 11 0 0 16 Feb 2024
PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance Haichao Sha Ruixuan Liu Yi-xiao Liu Hong Chen 41 1 0 06 Dec 2023
Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacy Yi Shi Kang Wei Li Shen Yingqi Liu Xueqian Wang Bo Yuan Dacheng Tao FedML 28 2 0 01 May 2023
Differentially Private Fine-tuning of Language Models Da Yu Saurabh Naik A. Backurs Sivakanth Gopi Huseyin A. Inan ... Y. Lee Andre Manoel Lukas Wutschitz Sergey Yekhanin Huishuai Zhang 134 344 0 13 Oct 2021
Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning Da Yu Huishuai Zhang Wei Chen Tie-Yan Liu FedML SILM 91 110 0 25 Feb 2021
Tempered Sigmoid Activations for Deep Learning with Differential Privacy Nicolas Papernot Abhradeep Thakurta Shuang Song Steve Chien Ulfar Erlingsson AAML 128 178 0 28 Jul 2020