Research map / Federated learning and privacy / Differential privacy
Decoupling Regularization and Privacy in Differentially Private Ridge Regression and ERM
Wanjie Wang, Tathagata Banerjee
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 |
|---|---|---|---|
| decouple statistical penalty alpha from privacy-stabilization parameter c | DP ridge regression (DADP) · synthetic, error vs n (p=n^0.4/2 and p=n^0.6/5) | parameter error | Improved |
| decouple alpha and c | DP ridge regression (DADP) · synthetic, error vs privacy budget epsilon (n=20000) | parameter error | Improved |
| decouple alpha and c | DP ridge regression (DADP) · California housing (eps=1) | normalized parameter error: 0.31 vs 1.42 (ObjPert-LD) | Improved |
| decouple alpha and c | DP ridge regression (DADP) · Boston Housing (eps=1) | normalized parameter error: 0.63 vs 22.9 (CWZ-LD) | Improved |
| baselines Private-JL and CWZ-HD in the harder regime p=n^0.6/5 | JL and CWZ-HD baselines · synthetic, p=n^0.6/5 | parameter error | Hurt |
Closest papers by meaning
- Differentially Private Coordinate Descent for Composite Empirical Risk Minimization (ICML 2022 · similarity 0.88)
- Optimal Ridge Regularization for Out-of-Distribution Prediction (ICML 2024 · similarity 0.87)
- On Inherent Privacy of Posterior Sampling: A Unified R\'enyi-Divergence Framework (NeurIPS 2026 · similarity 0.87)
- Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training (NeurIPS 2024 · similarity 0.87)
- Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation (ICML 2024 · similarity 0.86)
- Online Sensitivity Optimization in Differentially Private Learning (AAAI 2024 · similarity 0.86)
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.
