all AI news
How Private is DP-SGD?
March 27, 2024, 4:42 a.m. | Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang
cs.LG updates on arXiv.org arxiv.org
Abstract: We demonstrate a substantial gap between the privacy guarantees of the Adaptive Batch Linear Queries (ABLQ) mechanism under different types of batch sampling: (i) Shuffling, and (ii) Poisson subsampling; the typical analysis of Differentially Private Stochastic Gradient Descent (DP-SGD) follows by interpreting it as a post-processing of ABLQ. While shuffling based DP-SGD is more commonly used in practical implementations, it is neither analytically nor numerically amenable to easy privacy analysis. On the other hand, Poisson …
abstract analysis arxiv cs.cr cs.ds cs.lg gap gradient linear post-processing privacy processing queries sampling stochastic type types
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote