Research map / Federated learning and privacy / Differential privacy
Composition Theorems for Interactive Differential Privacy
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 |
|---|---|---|---|
| Allow arbitrary interleaving of queries among independently running mechanisms | Interactive mechanisms satisfying approximate DP · Concurrent composition | approximate DP guarantee: the optimal (sequential) composition theorem | No clear effect |
| Allow arbitrary interleaving of queries among independently running mechanisms | Interactive mechanisms satisfying RDP · Concurrent composition | RDP guarantee: (α, ε_1 + ... + ε_k)-RDP | No clear effect |
| Allow arbitrary interleaving of queries among independently running mechanisms | Interactive mechanisms satisfying zCDP · Concurrent composition | zCDP guarantee: (sum_i η_i)-zCDP | No clear effect |
| Allow arbitrary interleaving of queries among independently running mechanisms | Interactive mechanisms satisfying tCDP · Concurrent composition | tCDP guarantee: (sum_i ρ_i, ω)-tCDP | No clear effect |
Closest papers by meaning
- Fully-Adaptive Composition in Differential Privacy (ICML 2023 · similarity 0.90)
- Optimal Differential Privacy Composition for Exponential Mechanisms (ICML 2020 · similarity 0.89)
- Privacy Odometers and Filters: Pay-as-you-Go Composition (NeurIPS 2016 · similarity 0.88)
- Optimality of Matrix Mechanism on $\ell_p^p$-metric (ICLR 2025 · similarity 0.87)
- Purifying Approximate Differential Privacy with Randomized Post-processing (NeurIPS 2025 · similarity 0.86)
- On Differential Privacy for Adaptively Solving Search Problems via Sketching (ICML 2025 · 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.