Research map / Federated learning and privacy / Differential privacy
Anonymized Histograms in Intermediate Privacy Models
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
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 |
|---|---|---|---|
| Hash the domain into B = O(n) buckets before estimating | Noisy histogram post-processing · Anonymized histogram with large D | expected ℓ1-error: \widetilde{O}_\varepsilon(\sqrt{n}) | Improved |
| Use a low-sensitivity symmetric estimator on the private anonymized histogram | Private estimation of symmetric distribution properties · Symmetric distribution properties | sample complexity: O\inparen{C_{\hat{f}}\inparen{f, \frac\alpha2} + D_{\hat{f}}\inparen{\frac\alpha2, \varepsilon}} | Improved |
Closest papers by meaning
- Differentially Private Anonymized Histograms (NeurIPS 2019 · similarity 0.95)
- Algorithms for bounding contribution for histogram estimation under user-level privacy (ICML 2023 · similarity 0.90)
- INSPECTRE: Privately Estimating the Unseen (ICML 2018 · similarity 0.88)
- The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space (NeurIPS 2020 · similarity 0.88)
- In Differential Privacy, There is Truth: on Vote-Histogram Leakage in Ensemble Private Learning (NeurIPS 2022 · similarity 0.88)
- A Generalized Shuffle Framework for Privacy Amplification: Strengthening Privacy Guarantees and Enhancing Utility (AAAI 2024 · 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.
