Research map / Learning theory and algorithms / Clustering
The Hidden Convexity of Spectral Clustering
James Voss, Mikhail Belkin, Luis Rademacher
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 |
|---|---|---|---|
| replace spherical k-means with HBRopt (g_sig) basis recovery on spectral embedding | spectral clustering · Imbalanced stochastic block model | mean accuracy (%): 42.1 -> 99.9 | Improved |
| replace spherical k-means with HBRopt g_abs | spectral clustering · thyroid | accuracy (%): 80.4 -> 82.4 | Improved |
| replace spherical k-means with HBRopt g_abs | spectral clustering · E. coli | accuracy (%): 69.0 -> 80.9 | Improved |
| replace spherical k-means with HBRopt g_abs | spectral clustering · Iris | accuracy (%): 84.0 -> 82.8 | Hurt |
| replace spherical k-means with HBRopt g_abs | spectral clustering · car eval | accuracy (%): 36.4 -> 37.0 | Improved |
| replace spherical k-means with HBRopt g_abs | spectral clustering · glass | accuracy (%): 46.8 -> 47.0 | Mixed |
| choose HBRenum with g_abs or g_ht contrast instead of g_gau or g_sig (ablation) | HBRenum · E. coli | accuracy (%): 81.5 -> 68.7 | Hurt |
| choose HBRenum g_sig instead of g_abs (ablation) | HBRenum · Iris | accuracy (%): 67.3 -> 84.0 | Improved |
| choose HBRenum g_3 instead of g_sig (ablation) | HBRenum · car eval | accuracy (%): 41.1 -> 41.1 | No clear effect |
| HBRopt with g_3 instead of g_abs (ablation) | HBRopt · Iris | accuracy (%): 82.8 -> 78.5 | Hurt |
| HBRopt/HBRenum vs spherical k-means overall | spectral clustering · UCI datasets | accuracy | Mixed |
Closest papers by meaning
- A Novel and Effective Method to Directly Solve Spectral Clustering (TPAMI 2024 · similarity 0.89)
- Connecting Spectral Clustering to Maximum Margins and Level Sets (JMLR 2020 · similarity 0.89)
- Accelerating Spectral Clustering under Fairness Constraints (ICML 2025 · similarity 0.88)
- Equivalence between Graph Spectral Clustering and Column Subset Selection (Student Abstract) (AAAI 2024 · similarity 0.88)
- Structure-Aware Spectral Sparsification via Uniform Edge Sampling (NeurIPS 2025 · similarity 0.88)
- Pass-Efficient Algorithms for Graph Spectral Clustering (Student Abstract) (AAAI 2024 · similarity 0.87)
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.
