Research map / Learning theory and algorithms / Clustering
Optimal Cluster Recovery in the Labeled Stochastic Block Model
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 |
|---|---|---|---|
| Use Spectral Partition under the stated parameter condition and assumption (A3) | LSBM cluster recovery · LSBM, at most s misclassified items | misclassified items: at most s items with high probability | Helped |
| Use Spectral Partition when the exact-recovery condition and assumption (A3) hold | LSBM cluster recovery · LSBM, exact cluster recovery | misclassified items: recovers the clusters exactly with high probability | Helped |
| Apply any clustering algorithm when nD(α,p)/log(n/s) falls below the necessary threshold | LSBM cluster recovery · LSBM, expected misclassified items | expected misclassified items: liminf_{n→∞} nD(α,p)/log(n/s) ≥ 1 | Hurt |
| Add iterative likelihood-based cluster improvement after spectral initialization | SP spectral initialization · LSBM, items in H | misclassified items: |E^(t+1) ∩ H|/|E^(t) ∩ H| ≤ 1/√(n p̄) | Helped |
Closest papers by meaning
- Revisiting Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model (ICML 2025 · similarity 0.94)
- Optimal Graph Clustering without Edge Density Signals (NeurIPS 2025 · similarity 0.89)
- Exact Community Recovery under Side Information: Optimality of Spectral Algorithms (ICLR 2025 · similarity 0.89)
- Differentially private exact recovery for stochastic block models (ICML 2024 · similarity 0.89)
- On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models (NeurIPS 2024 · similarity 0.89)
- Efficient Graph Matching for Correlated Stochastic Block Models (NeurIPS 2024 · similarity 0.88)
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.