Research map / Learning theory and algorithms / Clustering
On Generalization Bounds for Projective Clustering
Maria Sofia Bucarelli, Matilde Fjeldsø Larsen, Chris Schwiegelshohn, Mads Toftrup
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 |
|---|---|---|---|
| compare empirical k-exponent to theoretical value | center-based clustering · Covtype, Mushroom, Skin_Nonskin, MNIST | fitted exponent q1: 0.5 -> 0.44 | Improved |
| compare empirical n-exponent to theoretical value | center-based clustering · real datasets | fitted exponent q2: 0.5 -> 0.52 | No clear effect |
| increase power z from 1 to 4 (ablation) | center-based clustering · Covtype | fitted q1 and q2: 0.44 -> 0.44 | No clear effect |
| increase power z (ablation) | subspace clustering · Covtype, j=1 | excess risk decrease rate | Improved |
| increase subspace dimension j (ablation) | subspace clustering · real datasets | fitted exponents | No clear effect |
| increase number of clusters k (ablation) | subspace clustering · real datasets | dependency on k | Mixed |
| assume margin or stability conditions hold in practice | clustering generalization bounds · real datasets | learning rate | No clear effect |
Closest papers by meaning
- Sharper Generalization Bounds for Clustering (ICML 2021 · similarity 0.87)
- Global Optimization of K-Center Clustering (ICML 2022 · similarity 0.86)
- Improved Fixed-Parameter Bounds for Min-Sum-Radii and Diameters k-Clustering and Their Fair Variants (AAAI 2025 · similarity 0.85)
- Beyond Worst-Case Coreset Bounds for $k$-Clustering via Determinantal Sampling (NeurIPS 2026 · similarity 0.85)
- Approximately Pareto-optimal Solutions for Bi-Objective k-Clustering (NeurIPS 2024 · similarity 0.85)
- New Bounds on the Cohesion of Complete-link and Other Linkage Methods for Agglomerative Clustering (ICML 2024 · 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.
