Research map / Federated learning and privacy / Differential privacy
Brownian Noise Reduction: Maximizing Privacy Subject to Accuracy Constraints
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 |
|---|---|---|---|
| Use the Brownian mechanism instead of Laplace noise reduction | Private logistic regression · KDD-99 | loss | Helped |
| Use the Brownian mechanism instead of Laplace noise reduction | Private ridge regression · Twitter | loss | Helped |
| Use the Brownian mechanism instead of Laplace noise reduction | Private logistic regression · KDD-99 | median privacy loss | Helped |
| Use the Brownian mechanism instead of Laplace noise reduction | Private ridge regression · Twitter | median privacy loss | Helped |
| Use the Brownian mechanism instead of Laplace noise reduction | Private logistic regression · KDD-99 | privacy loss distribution concentration | Helped |
| Use the Brownian mechanism instead of Laplace noise reduction | Private ridge regression · Twitter | privacy loss distribution concentration | Helped |
| Use ReducedAboveThreshold instead of AboveThreshold to privately check accuracy | Brownian mechanism · Logistic regression and ridge regression | median privacy loss | Helped |
| Use ReducedAboveThreshold instead of AboveThreshold to privately check accuracy | Brownian mechanism · Logistic regression and ridge regression | privacy loss variance | Hurt |
Closest papers by meaning
- Rényi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration via Shift Reduction Lemmas (ICML 2024 · similarity 0.89)
- Privacy Guarantees in Posterior Sampling under Contamination (NeurIPS 2026 · similarity 0.89)
- Private Adaptive Covariance Estimation via Gaussian Graphical Models (NeurIPS 2026 · similarity 0.89)
- Optimizing Noise Distributions for Differential Privacy (ICML 2025 · similarity 0.89)
- Attack-Aware Noise Calibration for Differential Privacy (NeurIPS 2024 · similarity 0.89)
- Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy (ICML 2024 · similarity 0.89)
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.