Research map / Federated learning and privacy / Differential privacy
Fast Optimal Locally Private Mean Estimation via Random Projections
Hilal Asi, Vitaly Feldman, Jelani Nelson, Huy Nguyen, Kunal Talwar
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 |
|---|---|---|---|
| increase communication budget k up to 1000 (ablation) | random-projection private mean estimator · Synthetic mean estimation d=32768 | squared error: k up to 1000 | Improved |
| use correlated transformations (ablation) | fast projection protocol · Synthetic mean estimation | squared error | No clear effect |
| use SRHT instead of random rotations (ablation) | projection protocol · Run-time vs dimension | run-time | Improved |
| compare against low-communication baselines | ours vs HS and SQKR · Synthetic mean estimation | squared error | Improved |
| DP-SGD clipping without noise | DP-SGD · MNIST | test accuracy: 98 -> 91 | Hurt |
Closest papers by meaning
- Public-data Assisted Private Stochastic Optimization: Power and Limitations (NeurIPS 2024 · similarity 0.87)
- Instance-Optimality for Private KL Distribution Estimation (NeurIPS 2025 · similarity 0.85)
- Better Locally Private Sparse Estimation Given Multiple Samples Per User (ICML 2024 · similarity 0.85)
- Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messages (ICML 2024 · similarity 0.85)
- On Differentially Private Subspace Estimation in a Distribution-Free Setting (NeurIPS 2024 · similarity 0.85)
- Differentially Private Optimization with Sparse Gradients (NeurIPS 2024 · similarity 0.85)
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.
