AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Oblivious Sampling Algorithms for Private Data Analysis

Sajin Sasy, Olga Ohrimenko

NeurIPS 2019 · Federated learning and privacy › Differential privacy · approach: Private training with public data · 4 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 Poisson sampling instead of shufflingDP MNIST training · DP MNISTtest accuracy: 94.06 -> 94.1No clear effect
Use SWO instead of shufflingDP MNIST training · DP MNISTtest accuracy: 94.06 -> 94.03No clear effect
Use SWO instead of shufflingDP CIFAR-10 training · DP CIFAR-10test accuracy: 73.4 -> 72.5No clear effect
Use Poisson sampling instead of shufflingDP MNIST training · DP MNISTepsilon: 9.39 -> 0.82Improved
Use SWO instead of shufflingDP MNIST training · DP MNISTepsilon: 9.39 -> 2.13Improved
Use SWO instead of shufflingDP CIFAR-10 training · DP CIFAR-10epsilon: 9.39 -> 4.89Improved

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