Research map / Federated learning and privacy / Differential privacy
The Skellam Mechanism for Differentially Private Federated 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 |
|---|---|---|---|
| use distributed Skellam instead of analytic Gaussian | Skellam mechanism · distributed mean estimation | MSE | No clear effect |
| use Skellam instead of distributed discrete Gaussian | Skellam mechanism · Federated EMNIST/Shakespeare/SO-NWP | test accuracy | No clear effect |
| use Skellam instead of continuous Gaussian under secure aggregation | Skellam mechanism · Federated EMNIST/Shakespeare/SO-NWP | test accuracy | No clear effect |
| use Skellam sampler instead of non-vectorized discrete Gaussian sampler | Skellam mechanism · sampling time | sampling time: 1000x slower | Helped |
| use Skellam sampler instead of vectorized discrete Gaussian sampler | Skellam mechanism · sampling time | sampling time: up to 40% slower | Helped |
Closest papers by meaning
- Sketched Gaussian Mechanism for Private Federated Learning (NeurIPS 2025 · similarity 0.89)
- DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing (ICML 2025 · similarity 0.89)
- Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy (NeurIPS 2025 · similarity 0.88)
- Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation (ICML 2025 · similarity 0.88)
- Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systems (ICML 2024 · similarity 0.88)
- Differentially Private Decentralized Learning with Random Walks (ICML 2024 · 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.