Research map / Learning theory and algorithms / Clustering
Selective Sampling-based Scalable Sparse Subspace Clustering
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 |
|---|---|---|---|
| replace random subsampling with subgradient-based selective sampling (ablation) | S5C · Yale B | objective value vs number of subsamples: ~75% of subsamples reach the same objective as S5C-rand | Helped |
| use orthogonal iteration instead of exact NCut eigendecomposition for spectral clustering (ablation) | S5C · COIL-100 | clustering error (%): 47.0 -> 45.4 (time 290.0 -> 27.4 s) | No clear effect |
| use orthogonal iteration (block of eigenvectors) instead of power iteration clustering (ablation) | S5C spectral step · Yale B | clustering error (%): 83.9 -> 42.8 | Helped |
| use orthogonal iteration instead of PIC (ablation) | S5C spectral step · COIL-100 | clustering error (%): 77.4 -> 45.4 | Helped |
| use orthogonal iteration instead of PIC (ablation) | S5C spectral step · COIL-100 | time (s): 16.4 -> 27.4 | Hurt |
| S5C vs SSC-ORGEN across datasets | S5C · six real datasets | clustering error (%): Yale B 37.4 -> 39.3; COIL-100 89.7 -> 45.9; MNIST 28.7 -> 40.4 | Mixed |
Closest papers by meaning
- Stochastic Sparse Subspace Clustering (CVPR 2020 · similarity 0.91)
- Sparse Subspace Clustering with Entropy-Norm (ICML 2020 · similarity 0.90)
- Theoretical Analysis of Sparse Subspace Clustering with Missing Entries (ICML 2018 · similarity 0.90)
- Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuit (CVPR 2016 · similarity 0.89)
- Heterogeneous Sufficient Dimension Reduction and Subspace Clustering (ICML 2025 · similarity 0.87)
- Exploring a Principled Framework for Deep Subspace Clustering (ICLR 2025 · 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.