AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Improving Sparse Vector Technique with Renyi Differential Privacy

Yuqing Zhu, Yu-Xiang Wang

NeurIPS 2020 · Federated learning and privacy › Differential privacy · approach: Private online and user-level learning · 3 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
Use Gaussian-SVT instead of Laplace-SVT when threshold T is largeSparse Vector Technique · Exp 1, T=700, c=20, delta=1e-10number of answered queriesImproved
Use stage-wise Gaussian-SVT with hybrid composition instead of Laplace-SVTGaussian-SVT · Exp 1number of answered queriesImproved
Use RDP sinh-style bound for Laplace-SVT instead of CDP versionLaplace-SVT · Exp 1number of answered queriesImproved
Gaussian-SVT vs Laplace-SVT with same noise varianceSVT · Exp 2, synthetic null sequencecomposed privacy lossImproved
Gaussian mechanism or noisy screening instead of Gaussian-SVT for few iterationsGaussian-SVT · Exp 2, small number of iterationscomposed privacy lossHurt
Gaussian-SVT instead of data-dependent noisy-screeningprivate kNN query release · Exp 3, CIFAR-10expected privacy lossImproved

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