Research map / Federated learning and privacy / Differential privacy
Renyi Differential Privacy of The Subsampled Shuffle Model In Distributed Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Replace standard composition with the proposed subsampled-shuffle RDP analysis | CLDP-SGD with ℓ∞ clipping · MNIST test, privacy budget ε=1.4 | accuracy: 70.7%(± 2.1) -> 80%(± 1.8) | Helped |
| Replace strong composition with the proposed subsampled-shuffle RDP analysis | CLDP-SGD with ℓ∞ clipping · MNIST test, accuracy 90% | privacy budget ε: 4.82 -> 2.91 | Helped |
| Replace standard composition with the proposed subsampled-shuffle RDP analysis | CLDP-SGD with ℓ2 clipping · MNIST test, privacy budget ε=3 | accuracy: 76.46%(± 1.9) -> 81.15%(± 0.7) | Helped |
| Replace strong composition with the proposed subsampled-shuffle RDP analysis | CLDP-SGD with ℓ2 clipping · MNIST test, accuracy 89.7% | privacy budget ε: 18.3 -> 5.8 | Helped |
| Use the proposed RDP bound for composition instead of shuffled approximate-DP bounds with strong composition | Subsampled-shuffle mechanisms · T=10^5, γ=0.001, ε₀=2, n=10^6 | privacy budget ε: 14× saving | Helped |
Closest papers by meaning
- Leveraging Randomness in Model and Data Partitioning for Privacy Amplification (ICML 2025 · similarity 0.91)
- A Generalized Shuffle Framework for Privacy Amplification: Strengthening Privacy Guarantees and Enhancing Utility (AAAI 2024 · similarity 0.91)
- Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation (ICML 2025 · similarity 0.90)
- Learning from End User Data with Shuffled Differential Privacy over Kernel Densities (ICLR 2025 · similarity 0.90)
- Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement (NeurIPS 2024 · similarity 0.90)
- Privacy amplification by random allocation (NeurIPS 2025 · similarity 0.90)
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.