Dynamic Privacy Budget Allocation Improves Data Efficiency of
Differentially Private Gradient Descent

v1v2v3 (latest)

Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent

19 January 2021

ArXiv (abs)PDF HTML

Papers citing "Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent"

5 / 5 papers shown

Title
BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocation Xianzhi Zhang Yipeng Zhou Di Wu Di Wu Pengshan Liao Mohsen Guizani Michael Sheng 102 0 0 04 Dec 2024
Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyond Shanshan Han 167 1 0 09 Oct 2024
DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction Xinwei Zhang Zhiqi Bu Mingyi Hong Meisam Razaviyayn 70 5 0 24 Aug 2024
Distributed Harmonization: Federated Clustered Batch Effect Adjustment and Generalization Hoang Bao Yijiang Pang Siqi Liang Liang Zhan Paul Thompson Jiayu Zhou FedML 73 2 0 23 May 2024
Why Is Public Pretraining Necessary for Private Model Training? Arun Ganesh Mahdi Haghifam Milad Nasr Sewoong Oh Thomas Steinke Om Thakkar Abhradeep Thakurta Lun Wang 68 39 0 19 Feb 2023