Research map / Federated learning and privacy / Differential privacy
KNG: The K-Norm Gradient Mechanism
Matthew Reimherr, Jordan Awan
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 KNG instead of the exponential mechanism | differentially private linear regression · Linear regression simulation (d=12, eps=1) | average L2 distance to truth | Improved |
| use KNG instead of objective perturbation | differentially private linear regression · Linear regression simulation (d=12, eps=1) | average L2 distance to truth | No clear effect |
| use KNG instead of the exponential mechanism | differentially private quantile regression · Quantile regression simulation (tau=1/2, eps=1) | average L2 distance to truth | Improved |
Closest papers by meaning
- Brownian Noise Reduction: Maximizing Privacy Subject to Accuracy Constraints (NeurIPS 2022 · similarity 0.86)
- Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising (ICML 2018 · similarity 0.86)
- An Optimal and Scalable Matrix Mechanism for Noisy Marginals under Convex Loss Functions (NeurIPS 2023 · similarity 0.86)
- Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation (NeurIPS 2019 · similarity 0.85)
- DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction (ICLR 2025 · similarity 0.85)
- 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.
