VC-Dimension of Geometric Classifiers Explored for Active Learning

This paper delves into the theoretical underpinnings of generalization in geometric machine learning by computing the VC-dimension for metric ball classifiers across various geometric spaces. It establishes bounds for these classifiers in Euclidean, spherical, and hyperbolic geometries, as well as in general normed vector spaces and Riemannian manifolds. The research also explores generalization bounds using covering arguments for data on low-dimensional subsets of high-dimensional Euclidean spaces, with a specific application to active learning algorithms. AI

IMPACT Provides theoretical bounds for generalization in geometric machine learning, potentially improving active learning algorithms.

RANK_REASON The cluster contains a single academic paper detailing theoretical research in machine learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• active learning
• $\\ell^p$-norms
• Euclidean
• metric ball classifiers
• normed vector spaces
• Riemannian geometry
• Riemannian manifold
• spherical
• Stephan Wojtowytsch
• VC dimension

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →