Research map / Federated learning and privacy / Differential privacy
cpSGD: Communication-efficient and differentially-private distributed SGD
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 |
|---|---|---|---|
| Add randomized Walsh-Hadamard rotation before quantization (ablation) | Stochastic k-level quantization + Binomial mechanism · Distributed mean estimation | communication: n \cdot d \cdot \left(\log_2 \left(\sqrt{d} + \frac{d}{n \varepsilon^2} \right) + \mathcal{O}( \log \log \left(\frac{nd} | Helped |
| Add randomized Walsh-Hadamard rotation before quantization (ablation) | Stochastic k-level quantization + Binomial mechanism · Distributed mean estimation | mean squared error: \frac{dD^2}{n(k-1)^2} + \frac{d}{n}\cdot\frac{4mp(1-p) D^2}{(k-1)^2} -> \frac{2 \log \frac{2nd}{\delta} \cdot D^2}{n(k-1 | Helped |
| Use the Binomial mechanism instead of Gaussian noise | Privacy mechanism for discrete-valued data · Binomial mechanism | utility at a given privacy level | No clear effect |
| Improve the sufficient N bound for the p = 1/2 Binomial mechanism | Binomial mechanism · Differentially private discrete query release | required N: N needs to be ≥ 64 log(2/δ)/ε^2 -> N ≥ 8 log(2/δ)/ε^2 | Helped |
Closest papers by meaning
- The Privacy Power of Correlated Noise in Decentralized Learning (ICML 2024 · similarity 0.90)
- Noisy SIGNSGD Is More Differentially Private Than You (Might) Think (ICML 2025 · similarity 0.89)
- Faster Algorithms for User-Level Private Stochastic Convex Optimization (NeurIPS 2024 · similarity 0.89)
- Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systems (ICML 2024 · similarity 0.88)
- Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness (ICLR 2025 · similarity 0.88)
- Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation (ICML 2025 · similarity 0.88)
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.