Research map / Learning theory and algorithms / Matrix and tensor methods
Exploiting Tradeoffs for Exact Recovery in Heterogeneous Stochastic Block Models
Amin Jalali, Qiyang Han, Ioana Dumitriu, Maryam Fazel
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 per-community relative density rho_k instead of (p_min, n_min) as the summary statistic | Theorem 3 (modified ML estimator) · Example 1: two communities n-sqrt(n) and sqrt(n) | exact recovery guarantee | Improved |
| use Theorem 1 conditions with a few very dense tiny communities of size sqrt(log n) | SDP convex recovery (2.4) · Example 3: smallest community size | exact recovery guarantee | Improved |
| switch from Theorem 1 to Theorem 2 conditions to allow many small communities (smallest size O(log n)) | SDP convex recovery (2.4) · Example 5: many log n-size communities, spread sizes | exact recovery guarantee | Mixed |
| apply Theorem 3 (modified ML) instead of convex Theorems 1 or 2 when p_min - q is O(1) | recoverability analysis · Example 6: dense graph, small p_min - q | smallest recoverable community size | Improved |
| use SDP convex recovery instead of the peeling strategy of [3] | heterogeneous SBM with one big community and many small dense ones · Example 4 | exact recovery of all communities | Improved |
Closest papers by meaning
- Differentially private exact recovery for stochastic block models (ICML 2024 · similarity 0.94)
- Query-Limited Community Recovery in Stochastic Block Models (NeurIPS 2026 · similarity 0.91)
- Harnessing Multiple Correlated Networks for Exact Community Recovery (NeurIPS 2024 · similarity 0.90)
- Exact Community Recovery under Side Information: Optimality of Spectral Algorithms (ICLR 2025 · similarity 0.90)
- Revisiting Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model (ICML 2025 · similarity 0.89)
- Efficient Graph Matching for Correlated Stochastic Block Models (NeurIPS 2024 · similarity 0.89)
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.
