Research map / Learning theory and algorithms / Sample complexity
Sharp Impossibility Results for Hyper-graph Testing
Jiashun Jin, Tracy Ke, Jiajun Liang
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 asymmetric community sizes (375 vs 125 nodes) instead of symmetric (250 vs 250) in the SBM alternative | degree-based chi-square statistic psi_n · Simulated 3-uniform SBM, n=500, K=2 | separation of psi_n from N(0,1) null | Improved |
| apply degree matching (theta* from tensor scaling) when building the DCBM alternative | degree-based chi-square statistic psi_n · Simulated DCBM, n=500, K=2, Pareto theta, c_n=n^-1 | separation of null and alternative histograms of psi_n | Hurt |
| use the proposed scan statistic phi_n (with spectral-clustering proxy partition) instead of the degree-based psi_n, with signal raised to c_n=n^-1/2 | least-favorable DCBM pair · Simulated DCBM, n=500, K=2, m=3 | separation of null and alternative histograms | Improved |
| replace exact maximization over partitions with a spectral-clustering proxy partition in phi_n (ablation) | phi_n test statistic · Simulated DCBM, n=500 | testing performance | No clear effect |
Closest papers by meaning
- Edge-Colored Clustering in Hypergraphs: Beyond Minimizing Unsatisfied Edges (ICML 2025 · similarity 0.86)
- Optimal community detection in dense bipartite graphs (NeurIPS 2025 · similarity 0.85)
- Optimal Quasi-clique: Hardness, Equivalence with Densest-k-Subgraph, and Quasi-partitioned Community Mining (AAAI 2024 · similarity 0.85)
- Efficient Graph Matching for Correlated Stochastic Block Models (NeurIPS 2024 · similarity 0.84)
- Harnessing Multiple Correlated Networks for Exact Community Recovery (NeurIPS 2024 · similarity 0.84)
- Replicability in Learning: Geometric Partitions and KKM-Sperner Lemma (NeurIPS 2024 · similarity 0.84)
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.
