Research map / Federated learning and privacy / Differential privacy
Oblivious Sampling Algorithms for Private Data Analysis
Sajin Sasy, Olga Ohrimenko
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use Poisson sampling instead of shuffling | DP MNIST training · DP MNIST | test accuracy: 94.06 -> 94.1 | No clear effect |
| Use SWO instead of shuffling | DP MNIST training · DP MNIST | test accuracy: 94.06 -> 94.03 | No clear effect |
| Use SWO instead of shuffling | DP CIFAR-10 training · DP CIFAR-10 | test accuracy: 73.4 -> 72.5 | No clear effect |
| Use Poisson sampling instead of shuffling | DP MNIST training · DP MNIST | epsilon: 9.39 -> 0.82 | Improved |
| Use SWO instead of shuffling | DP MNIST training · DP MNIST | epsilon: 9.39 -> 2.13 | Improved |
| Use SWO instead of shuffling | DP CIFAR-10 training · DP CIFAR-10 | epsilon: 9.39 -> 4.89 | Improved |
Closest papers by meaning
- Privacy Guarantees in Posterior Sampling under Contamination (NeurIPS 2026 · similarity 0.88)
- How Private are DP-SGD Implementations? (ICML 2024 · similarity 0.88)
- Scalable DP-SGD: Shuffling vs. Poisson Subsampling (NeurIPS 2024 · similarity 0.88)
- Purifying Approximate Differential Privacy with Randomized Post-processing (NeurIPS 2025 · similarity 0.87)
- Distributed Differentially Private Data Analytics via Secure Sketching (ICML 2025 · similarity 0.87)
- Efficient Adaptive Data Analysis over Dense Data Distributions (NeurIPS 2026 · similarity 0.87)
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.
