Research map / Federated learning and privacy / Differential privacy
Differentially Private Coordinate Descent for Composite Empirical Risk Minimization
Paul Mangold, Aurélien Bellet, Joseph Salmon, Marc Tommasi
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 DP-CD instead of DP-SGD | DP-ERM · Electricity logistic regression and California LASSO (imbalanced) | relative error | Improved |
| use DP-CD instead of DP-SGD | DP-ERM · Standardized Electricity logistic regression, California LASSO, and Sparse LASSO (balanced) | relative error | Improved |
| use DP-CD instead of DP-SGD | DP-ERM · Numerical experiments | passes over the data: up to 10 times fewer passes | Improved |
| use DP-CD with privately estimated coordinate-wise smoothness constants | DP-CD · Electricity logistic regression and California LASSO (imbalanced) | relative error | Improved |
Closest papers by meaning
- Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement (NeurIPS 2024 · similarity 0.89)
- Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning (ICML 2025 · similarity 0.89)
- Differentially Private Optimization with Sparse Gradients (NeurIPS 2024 · similarity 0.89)
- Faster Algorithms for User-Level Private Stochastic Convex Optimization (NeurIPS 2024 · similarity 0.89)
- The importance of feature preprocessing for differentially private linear optimization (ICLR 2024 · similarity 0.89)
- Public-data Assisted Private Stochastic Optimization: Power and Limitations (NeurIPS 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.
