Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent - researchr publication related

researchr

You are not signed in
Sign in
Sign up

Junyuan Hong, Zhangyang Wang, Jiayu Zhou. Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent. In FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency, Seoul, Republic of Korea, June 21 - 24, 2022. pages 11-35, ACM, 2022. [doi]

The following publications are possibly variants of this publication:

Differentially Private Deep Learning With Dynamic Privacy Budget Allocation and Adaptive OptimizationLin Chen, Danyang Yue, Xiaofeng Ding 0001, Zuan Wang, Kim-Kwang Raymond Choo, Hai Jin 0001. tifs, 18:4422-4435, 2023. [doi]

Differentially private regression analysis with dynamic privacy allocationKe Pan, Maoguo Gong, Kaiyuan Feng, Kun Wang. kbs, 217:106795, 2021. [doi]

runs on WebDSL