New Study Computes VC-Dimension of Metric Ball Classifiers Across Riemannian Geometries
A new arXiv paper computes the VC-dimension of metric ball classifiers in Euclidean, spherical, and hyperbolic model spaces, presenting upper bounds with applications to active learning.
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-11-11 05:00 · arXiv stat.ML
VC-Dimension and Generalization in Geometric Machine Learning with Applications to Active Learning