Research map / Learning theory and algorithms / Clustering
Spectral learning of multivariate extremes
Marco Avella Medina, Richard A Davis, Gennady Samorodnitsky
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 spectral clustering instead of spherical k-means when noise is added to the linear factor model | clustering of extremes · Linear factor model with noise (sigma>0) | Frobenius estimation error of loadings | Improved |
| use spectral clustering instead of spherical k-means without noise | clustering of extremes · Linear factor model, sigma=0 | Frobenius estimation error of loadings | No clear effect |
| use spectral clustering instead of spherical k-means on MA(3) extremes with larger number of extremes | clustering of extremes · MA(3) bivariate extremes | estimation error variability | Mixed |
| vary the number of nearest neighbors k_n via constant C (ablation) | spectral clustering of extremes · MA(3) bivariate extremes | clustering performance | No clear effect |
| vary tail index alpha to 0.5 or 2 in the noisy factor model (ablation) | spectral clustering of extremes · Linear factor model with noise | relative performance vs spherical k-means | No clear effect |
Closest papers by meaning
- Feature Clustering for Support Identification in Extreme Regions (ICML 2021 · similarity 0.87)
- Connecting Spectral Clustering to Maximum Margins and Level Sets (JMLR 2020 · similarity 0.86)
- Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures (NeurIPS 2024 · similarity 0.86)
- A Random Matrix Analysis of Data Stream Clustering: Coping With Limited Memory Resources (ICML 2022 · similarity 0.86)
- On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models (NeurIPS 2024 · similarity 0.84)
- Structure-Aware Spectral Sparsification via Uniform Edge Sampling (NeurIPS 2025 · similarity 0.84)
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.
