Research map / Learning theory and algorithms / Clustering
A Sublinear-Time Spectral Clustering Oracle with Improved Preprocessing Time
Ranran Shen, Pan Peng
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 our dot-product spectral oracle instead of the prior random-walk l2 oracle (average error) | clustering oracle · SBM p=0.03 | misclassification error: 0.4970 -> 0.0003 | Improved |
| use our oracle instead of prior oracle at small conductance gap | clustering oracle · SBM p=0.025 | misclassification error: 0.6208 -> 0.0113 | Improved |
| use our oracle instead of prior oracle at p=0.035 | clustering oracle · SBM p=0.035 | misclassification error: 0.1996 -> 0 | Improved |
| use our oracle instead of prior oracle at p=0.05 | clustering oracle · SBM p=0.05 | misclassification error: 0.0168 -> 0 | Improved |
| use our oracle vs prior oracle at large gap p=0.06 and 0.07 | clustering oracle · SBM p=0.06, 0.07 | misclassification error: 0.0030 -> 0 and 0.0003 -> 0 | Improved |
| lower p to 0.02 (smaller conductance gap) for our oracle | our oracle · SBM n=3000 | misclassification error: 0.0113 -> 0.2273 | Hurt |
| increase p from 0.025 to 0.035 | our oracle · SBM n=3000 | misclassification error: 0.0113 -> 0 | Improved |
| prior oracle run-to-run variability (min vs max over 30 runs) | prior oracle · SBM p=0.04 | misclassification error: 0.0173 -> 0.4510 | Hurt |
| increase number of WhichCluster queries from 0 to 3200 | our oracle · SBM n=15000 | fraction of edges accessed: 0.1277 -> 0.9999 | Hurt |
| increase queries from 0 to 200 | our oracle · SBM n=15000 | fraction of edges accessed: 0.1277 -> 0.5377 | Mixed |
| increase p from 0.02 to 0.06 | our oracle · SBM n=3000 | query time (s): 0.3504 -> 0.4874 | Hurt |
| increase p from 0.02 to 0.06 | our oracle · SBM n=3000 | construct time (s): 11.6533 -> 12.5851 | No clear effect |
Closest papers by meaning
- Sublinear Spectral Clustering Oracle with Little Memory (ICLR 2026 · similarity 0.95)
- Pass-Efficient Algorithms for Graph Spectral Clustering (Student Abstract) (AAAI 2024 · similarity 0.89)
- Structure-Aware Spectral Sparsification via Uniform Edge Sampling (NeurIPS 2025 · similarity 0.88)
- Dynamic Correlation Clustering in Sublinear Update Time (ICML 2024 · similarity 0.87)
- Dynamic Spectral Clustering with Provable Approximation Guarantee (ICML 2024 · similarity 0.87)
- Equivalence between Graph Spectral Clustering and Column Subset Selection (Student Abstract) (AAAI 2024 · similarity 0.86)
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.
