Research map / Federated learning and privacy / Differential privacy
Differentially Private Distributed Data Summarization under Covariate Shift
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 private greedy selection instead of uniform sampling across data providers | Private Greedy · Allstate insurance, linear SVM | accuracy: 6% to 10% | Helped |
| add differential privacy to the greedy summarization | Non-Private Greedy · Allstate insurance | MMD^2 relative to non-private greedy | No clear effect |
| use private greedy instead of uniform sampling | Private Greedy · Allstate insurance | MMD^2 increase over greedy | Helped |
| use a small T (5 iterations) in subsequent epochs instead of d^1.5 (ablation) | Private Greedy · Allstate insurance | privacy and quality: 1656 -> 5 | Helped |
Closest papers by meaning
- Differentially private Bayesian learning on distributed data (NeurIPS 2017 · similarity 0.88)
- Differentially Private Submodular Maximization: Data Summarization in Disguise (ICML 2017 · similarity 0.88)
- Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods (NeurIPS 2021 · similarity 0.88)
- Differentially Private Sum-Product Networks (ICML 2024 · similarity 0.87)
- Scalable Private Partition Selection via Adaptive Weighting (ICML 2025 · similarity 0.87)
- Privacy Profiles for Private Selection (ICML 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.