Research map / Federated learning and privacy / Differential privacy
Integer Subspace 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 |
|---|---|---|---|
| Use the generalized Laplace mechanism for integer-valued noise that preserves the state population invariant | 2010 Census county-level population data · 2010 Census county-level population data, Illinois | population-size-dependent bias | Helped |
| Use the generalized Laplace mechanism with an ℓ1 target | Synthetic intersecting constraints · Synthetic intersecting constraints, ℓ1 target | iterations to empirical convergence: around 10^5 iterations | Mixed |
| Use the generalized Laplace mechanism with an ℓ2 target instead of an ℓ1 target | Synthetic intersecting constraints · Synthetic intersecting constraints, ℓ2 target | iterations to empirical convergence: 10^5 iterations -> 10^6 iterations | Hurt |
| Use the generalized Laplace mechanism with an ℓ1 target | Delinquent children contingency table · Delinquent children contingency table, ℓ1 target | iterations to empirical convergence: about 10^4 iterations | Helped |
Closest papers by meaning
- Subspace Differential Privacy (AAAI 2022 · similarity 0.94)
- Privacy amplification by random allocation (NeurIPS 2025 · similarity 0.88)
- Exactly Minimax-Optimal Locally Differentially Private Sampling (NeurIPS 2024 · similarity 0.88)
- Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation (NeurIPS 2026 · similarity 0.87)
- Privacy Profiles for Private Selection (ICML 2024 · similarity 0.87)
- On Differentially Private Subspace Estimation in a Distribution-Free Setting (NeurIPS 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.