Research map / Learning theory and algorithms / Sample complexity
Locally Private Hypothesis Testing
Or Sheffet
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 |
|---|---|---|---|
| Use the χ²-based test statistic under the null hypothesis | Non-symmetric identity testing · Identity testing | null-distribution fit to χ²_T: n=\{10,100,1000,10000\}; T=\{10,25,50,100\} | Improved |
| Increase sample size under the alternative hypothesis | Non-symmetric χ²-based identity test · Identity testing | separation from null χ² distribution: n=\{2500,5000,7500,10000,200000\}; α=\{0.25,0.2,0.15,0.1\} | Improved |
| Use Q(θ) as the test statistic for independence | Non-symmetric independence testing · Independence testing | separation between null and alternative: n = 25,000; α=0.25 | Mixed |
Closest papers by meaning
- Priv’IT: Private and Sample Efficient Identity Testing (ICML 2017 · similarity 0.91)
- Sort, Partition, Randomize: Optimal Binary Hypothesis Testing under Local Differential Privacy (NeurIPS 2026 · similarity 0.91)
- Minimax Optimal Two-Sample Testing under Local Differential Privacy (NeurIPS 2026 · similarity 0.89)
- Optimal Rates for Differentially Private Hypothesis Testing with E-values (NeurIPS 2026 · similarity 0.87)
- Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph (NeurIPS 2025 · similarity 0.87)
- Locally Optimal Private Sampling: Beyond the Global Minimax (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.
