Research map / Federated learning and privacy / Differential privacy
Differentially Private Covariance Estimation
Kareem Amin, Travis Dick, Alex Kulesza, Andres Munoz, Sergei Vassilvitskii
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 |
|---|---|---|---|
| use iterative eigenvector sampling instead of Gaussian mechanism (delta=0.001) | private covariance estimation · Wine/Adult/Airfoil | normalized Frobenius error | Improved |
| use iterative eigenvector sampling instead of Kapralov-Talwar (subtraction) updates | private covariance estimation · Wine/Adult/Airfoil | normalized Frobenius error | Improved |
| use iterative eigenvector sampling instead of Laplace mechanism | private covariance estimation · Wine/Adult/Airfoil | normalized Frobenius error | Improved |
| use iterative eigenvector sampling at epsilon=0.01 | private covariance estimation · Wine | normalized Frobenius error | Hurt |
| adaptive instead of uniform privacy budget splitting across eigenvectors (ablation) | iterative eigenvector sampling · Wine/Adult/Airfoil | normalized Frobenius error | No clear effect |
Closest papers by meaning
- Settling Pure Differentially Private Covariance Estimation (NeurIPS 2026 · similarity 0.91)
- Differentially Private Covariance Revisited (NeurIPS 2022 · similarity 0.90)
- Covariance-Aware Private Mean Estimation Without Private Covariance Estimation (NeurIPS 2021 · similarity 0.90)
- Private Adaptive Covariance Estimation via Gaussian Graphical Models (NeurIPS 2026 · similarity 0.89)
- An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise (NeurIPS 2025 · similarity 0.86)
- Instance-Specific Asymmetric Sensitivity in Differential Privacy (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.
