3 papers
cs.CR2025
PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance
Haichao Sha, Ruixuan Liu, Yixuan Liu +1
The paradigm of Differentially Private SGD~(DP-SGD) can provide a theoretical guarantee for training data in both centralized and federated settings. However, the utility degradati…
cs.CR2024
DPDR: Gradient Decomposition and Reconstruction for Differentially Private Deep Learning
Yixuan Liu, Li Xiong, Yuhan Liu +3
Differentially Private Stochastic Gradients Descent (DP-SGD) is a prominent paradigm for preserving privacy in deep learning. It ensures privacy by perturbing gradients with random…
cs.LG2024
Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails
Haichao Sha, Yang Cao, Yong Liu +3
Differentially Private Stochastic Gradient Descent (DPSGD) is widely utilized to preserve training data privacy in deep learning, which first clips the gradients to a predefined no…