BriefGPT.xyz
Mar, 2024
重尾扰动下的噪声(S)GD的差分隐私
Differential Privacy of Noisy (S)GD under Heavy-Tailed Perturbations
HTML
PDF
Umut Şimşekli, Mert Gürbüzbalaban, Sinan Yıldırım, Lingjiong Zhu
TL;DR
通过向随机梯度下降算法的迭代中注入重尾噪声,可以实现隐私保护,并且与高斯分布相比,重尾噪声具有相似的差分隐私保证,为一种可行的选择。
Abstract
Injecting
heavy-tailed noise
to the iterates of
stochastic gradient descent
(SGD) has received increasing attention over the past few years. While various theoretical properties of the resulting algorithm have be
→