Research map / Learning theory and algorithms / Sample complexity
Goodness-of-Fit Tests for Inhomogeneous Random Graphs
Soham Dan, Bhaswar B. Bhattacharya
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 Frobenius-norm statistic (Bootstrapped Frobenius / asymptotic test) instead of the edge-count test | goodness-of-fit testing of IER graphs · Erdos-Renyi, planted bisection, beta-model, m=4, n=100 | power vs separation | Mixed |
| Use the edge-count test instead of the Frobenius statistic in the graphon-based IER setting | Bootstrapped Edge Test · Graphon IER, n=100, varying m | power | Hurt |
| Use the Bootstrapped Frobenius Test on sparse 10-block SBM | Frobenius test vs edge test · Sparse 10-block SBM, n=100, m=4, d=0.3 | power | Improved |
| Use operator-norm spectral test for single-sample (m=1) goodness-of-fit instead of edge test | single-graph testing on Erdos-Renyi perturbation · ER(100,1/2) vs ER(100,1/2+Delta), m=1 | power | Improved |
| Use the Frobenius statistic with a bootstrap calibration when sample is small (m=4, n=100) | Frobenius-norm test · Erdos-Renyi, m=4, n=100 | power | Improved |
| Sample complexity: Frobenius/operator-norm test with n/eps^2 samples vs zero-norm testing | minimax testing · theory | sample complexity | No clear effect |
Closest papers by meaning
- Goodness-of-Fit Tests for Random Partitions via Symmetric Polynomials (JMLR 2018 · similarity 0.87)
- Optimal community detection in dense bipartite graphs (NeurIPS 2025 · similarity 0.86)
- Network two-sample test for block models (NeurIPS 2025 · similarity 0.86)
- Statistical Inference on Random Dot Product Graphs: a Survey (JMLR 2018 · similarity 0.86)
- Sample Complexity of Correlation Detection in the Gaussian Wigner Model (ICML 2025 · similarity 0.85)
- Fast Wasserstein rates for estimating probability distributions of probabilistic graphical models (NeurIPS 2026 · 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.
