Research map / Learning theory and algorithms / Sample complexity
Phase Transitions in the Detection of Correlated Databases
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 |
|---|---|---|---|
| Impose rho^2 d -> 0 (weak correlation in high dimension) and use thresholding of sum of X^T Y entries as the test | Gaussian correlated databases detection · d -> infinity | weak detection feasibility | No clear effect |
| Replace sum test with counting test over normalized pairwise correlations exceeding rho | Gaussian correlated databases detection · d fixed, n -> infinity | strong detection feasibility | Helped |
| Analysis of the counting test restricted to d=1 | phi_count · d=1 | strong detection feasibility | No clear effect |
Closest papers by meaning
- Sample Complexity of Correlation Detection in the Gaussian Wigner Model (ICML 2025 · similarity 0.88)
- Phase Transitions in the Pooled Data Problem (NeurIPS 2017 · similarity 0.87)
- Phase transition for detecting a small community in a large network (ICLR 2023 · similarity 0.85)
- Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks (NeurIPS 2024 · similarity 0.82)
- An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds (NeurIPS 2025 · similarity 0.82)
- Efficient Graph Matching for Correlated Stochastic Block Models (NeurIPS 2024 · similarity 0.82)
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.