The VC-dimension of axis-parallel boxes on the torus

DOI10.1016/j.jco.2021.101600zbMath1478.68286arXiv2004.13861OpenAlexW3194785620MaRDI QIDQ2052168

Pierre Gillibert, Thomas Lachmann, Clemens Müllner

Publication date: 25 November 2021

Published in: Journal of Complexity (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2004.13861

zbMATH Keywords

VC-dimensiondiscrepancy theorymeasure theorymachine learningsample compressionpoints on the torus

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05)

Related Items (1)

New bounds on the minimal dispersion

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Covering numbers, Vapnik-Červonenkis classes and bounds for the star-discrepancy
• Discrepancy and approximations for bounded VC-dimension
• Weak convergence and empirical processes. With applications to statistics
• A note on bounds for VC dimensions
• Sample Compression Schemes for VC Classes
• The inverse of the star-discrepancy depends linearly on the dimension
• Teaching and Compressing for Low VC-Dimension
• An Upper Bound of the Minimal Dispersion via Delta Covers
• Uniform Central Limit Theorems
• Understanding Machine Learning
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Geometric discrepancy. An illustrated guide

This page was built for publication: The VC-dimension of axis-parallel boxes on the torus