arXiv stat.ML
· Papers
Escaping Iterative Parameter-Space Noise: Differentially Private Learning with a Hypernetwork
arXiv:2606.26772v1 Announce Type: cross Abstract: Differentially private (DP) training of neural networks is often hindered by the large amount of noise required by gradient-based methods such as DP-SGD, which repeatedly inject high-dimensional noise in parameter space throughout training. In this paper, we propose a n