Research map / Federated learning and privacy / Differential privacy
Fully-Adaptive Composition in 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 |
|---|---|---|---|
| Measuring accumulated privacy loss in terms of intrinsic time determined by observed privacy parameters (rather than number of algorithms) | fully adaptive composition of differentially private algorithms · theoretical analysis (advanced composition with adaptively chosen privacy parameters) | rate of advanced composition | Helped |
| Reducing arbitrary conditionally differentially private algorithms to post-processings of conditional randomized response | adaptive composition for conditionally differentially private algorithms · theoretical analysis | required assumption for composition results | Helped |
Closest papers by meaning
- Privacy Odometers and Filters: Pay-as-you-Go Composition (NeurIPS 2016 · similarity 0.96)
- 𝑓-Differential Privacy Filters: Validity and Approximate Solutions (NeurIPS 2026 · similarity 0.90)
- The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD (ICLR 2025 · similarity 0.88)
- A Generalized Shuffle Framework for Privacy Amplification: Strengthening Privacy Guarantees and Enhancing Utility (AAAI 2024 · similarity 0.88)
- On Differential Privacy for Adaptively Solving Search Problems via Sketching (ICML 2025 · similarity 0.88)
- Purifying Approximate Differential Privacy with Randomized Post-processing (NeurIPS 2025 · similarity 0.87)
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.