Research map / Federated learning and privacy / Differential privacy
Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation
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 |
|---|---|---|---|
| Increase the trimming fraction from zero (ablation) | Trimmed mean · Gaussian data | mean squared error | Hurt |
| Increase trimming toward the median (ablation) | Trimmed mean · Laplacian data | variance | Helped |
| Use a small amount of trimming rather than none (ablation) | Trimmed mean · Mixture of two Gaussians with the same mean and differing variances | mean squared error | Helped |
| Increase trimming beyond the optimal fraction (ablation) | Trimmed mean · Mixture of two Gaussians with the same mean and differing variances | mean squared error | Hurt |
Closest papers by meaning
- Instance-optimal Mean Estimation Under Differential Privacy (NeurIPS 2021 · similarity 0.90)
- Privacy Guarantees in Posterior Sampling under Contamination (NeurIPS 2026 · similarity 0.90)
- On Inherent Privacy of Posterior Sampling: A Unified R\'enyi-Divergence Framework (NeurIPS 2026 · similarity 0.89)
- Locally Optimal Private Sampling: Beyond the Global Minimax (NeurIPS 2025 · similarity 0.88)
- Instance-Specific Asymmetric Sensitivity in Differential Privacy (NeurIPS 2024 · similarity 0.88)
- Mean Estimation in the Add-Remove Model of Differential Privacy (ICML 2024 · 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.