Research map / Federated learning and privacy / Differential privacy
User-Level Differential Privacy With Few Examples Per User
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Raghu Meka, Chiyuan Zhang
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 |
|---|---|---|---|
| user-level pure-DP PAC learning without requiring large m | User-level pure-DP PAC learning · theory, pure-DP | sample complexity bound | Improved |
| more examples per user m in agnostic PAC learning | Agnostic PAC learning · theory, pure-DP | sample complexity bound | Improved |
| first explicit pure user-level DP bounds for distribution learning | Discrete, product, Gaussian learning · theory, pure-DP | sample complexity bound | Improved |
| general approximate-DP transformation from item-level to user-level | Approximate-DP learning · theory, approximate-DP | sample complexity bound | Improved |
| approximate-DP discrete distribution bound versus prior user-level result | Discrete distribution learning · theory, approximate-DP | sample complexity bound | Mixed |
Closest papers by meaning
- Improved Bounds for Pure Private Agnostic Learning: Item-Level and User-Level Privacy (ICML 2024 · similarity 0.89)
- It's My Data Too: Private ML for Datasets with Multi-User Training Examples (ICML 2025 · similarity 0.88)
- The Limits of Differential Privacy in Online Learning (NeurIPS 2024 · similarity 0.87)
- Faster Algorithms for User-Level Private Stochastic Convex Optimization (NeurIPS 2024 · similarity 0.86)
- Learning from End User Data with Shuffled Differential Privacy over Kernel Densities (ICLR 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.
