Research map / Federated learning and privacy / Differential privacy
Prediction with Expert Advice under Local Differential Privacy
Ben Jacobsen, Kassem Fawaz
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 RW-Meta instead of central-DP Agarwal (Min Noise) | RW-Meta · COVID-19 hospital prediction, New Mexico, mu=1 | average gain: 22.83 -> 36.87 | Improved |
| tighten privacy from mu=infinity to mu=0.25 | RW-Meta · COVID-19 hospital prediction, New Mexico | average gain: 40.14 -> 22.46 | Hurt |
| tighten privacy from mu=infinity to mu=0.25 | RW-Meta · COVID-19 hospital prediction, California | average gain: 59.36 -> 33.34 | Hurt |
| tighten privacy from mu=infinity to mu=0.25 | Agarwal (Min Regret) · COVID-19 hospital prediction, Pennsylvania | average gain: 15.51 -> 15.35 | No clear effect |
| use RW-Meta instead of single best linear model | RW-Meta · COVID-19 hospital prediction, Pennsylvania, mu=0.25 | average gain: 28.73 -> 25.44 | Hurt |
Closest papers by meaning
- Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups (NeurIPS 2024 · similarity 0.87)
- Tracking The Best Expert Privately (ICML 2025 · similarity 0.87)
- Certification for Differentially Private Prediction in Gradient-Based Training (ICML 2025 · similarity 0.86)
- Private Online Learning via Lazy Algorithms (NeurIPS 2024 · similarity 0.86)
- Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting (ICML 2025 · similarity 0.86)
- Optimal Differentially Private Model Training with Public Data (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.
