AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification

Yingxue Zhou, Steven Wu, Arindam Banerjee

ICLR 2021 · Federated learning and privacy › Differential privacy · approach: DP-SGD refinements · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Project noisy gradients onto the top gradient eigenspace estimated from public data instead of using unprojected DP-SGDDP-SGD · MNIST, ε ≤ 0.42test accuracyImproved
Project noisy gradients onto the top gradient eigenspace estimated from public data instead of using unprojected DP-SGDDP-SGD · Fashion MNIST, ε ≤ 0.72test accuracyImproved
Project noisy gradients onto the top gradient eigenspace estimated from public data instead of using unprojected DP-SGDDP-SGD · MNIST and Fashion MNIST, large εaccuracyHurt
Replace the public-data gradient eigenspace with a Gaussian random projector (ablation)PDP-SGD · MNIST and Fashion MNISTaccuracyNo clear effect
Use a projection dimension of 10 rather than the larger tested dimensions (ablation)PDP-SGD · MNIST, ε = 0.23accuracyHurt
Increase the projection dimension among the tested values to 50 (ablation)PDP-SGD · MNIST, ε = 0.23accuracyImproved
Increase public sample size from 50 toward 150 (ablation)PDP-SGD · MNIST, ε = 0.23accuracyImproved
Increase public sample size from 100 to 150 (ablation)PDP-SGD · MNIST, ε = 0.23accuracyNo clear effect
Start projection at the 15th epoch instead of the 1st epoch (ablation)PDP-SGD and RPDP-SGD · Fashion MNISTaccuracyImproved
Update the eigenspace less frequently than every iteration (ablation)PDP-SGD · MNIST and Fashion MNISTaccuracyHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy