Research map / Federated learning and privacy / Differential privacy
Efficient Private Empirical Risk Minimization for High-dimensional Learning
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 |
|---|---|---|---|
| Run private ERM in a random projected subspace (compressed domain) and lift the solution back to original space (PROJERM) instead of operating on full d-dimensional data | private convex ERM for generalized linear losses · theoretical excess risk bounds | excess empirical risk bound | No clear effect |
| Use Lasso under epsilon-DP via compressed-domain PROJERM with logarithmic dependence on dimension | Lasso estimator under epsilon-differential privacy · theoretical excess risk | excess risk bound | Helped |
Closest papers by meaning
- Public-data Assisted Private Stochastic Optimization: Power and Limitations (NeurIPS 2024 · similarity 0.90)
- Differentially Private Optimization with Sparse Gradients (NeurIPS 2024 · similarity 0.89)
- Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning (ICML 2025 · similarity 0.89)
- On Differentially Private Subspace Estimation in a Distribution-Free Setting (NeurIPS 2024 · similarity 0.88)
- Differentially Private High-dimensional Variable Selection via Integer Programming (NeurIPS 2025 · similarity 0.88)
- On the Computational Complexity of Private High-dimensional Model Selection (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.