Research map / Learning theory and algorithms / Sample complexity
A Nearly-Linear Time Algorithm for Exact Community Recovery in 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 |
|---|---|---|---|
| Two-stage power method then generalized power method (vs. SDP, MGD, SC) | exact community recovery in binary symmetric SBM · Phase transition experiment, n=300 | total CPU time: 28 s vs 124 s (SC), 1063 s (MGD), 9193 s (SDP) | Helped |
| Generalized power method (GPM) second stage vs. manifold gradient descent (MGD) | convergence to ground truth · n=1000, 5000, 10000, alpha=10, beta=2 | iterations to exact recovery | Helped |
| Recovery performance of GPM vs. SDP, MGD, SC near information-theoretic threshold | exact community recovery · Phase transition experiment, n=300 | empirical exact recovery ratio | No clear effect |
Closest papers by meaning
- Differentially private exact recovery for stochastic block models (ICML 2024 · similarity 0.92)
- Efficient Graph Matching for Correlated Stochastic Block Models (NeurIPS 2024 · similarity 0.91)
- Harnessing Multiple Correlated Networks for Exact Community Recovery (NeurIPS 2024 · similarity 0.91)
- Query-Limited Community Recovery in Stochastic Block Models (NeurIPS 2026 · similarity 0.91)
- Revisiting Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model (ICML 2025 · similarity 0.90)
- Exact Community Recovery under Side Information: Optimality of Spectral Algorithms (ICLR 2025 · similarity 0.90)
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.