An Improved Uniform Convergence Bound with Fat-Shattering Dimension
Machine Learning
2023-07-14 v1 Machine Learning
Abstract
The fat-shattering dimension characterizes the uniform convergence property of real-valued functions. The state-of-the-art upper bounds feature a multiplicative squared logarithmic factor on the sample complexity, leaving an open gap with the existing lower bound. We provide an improved uniform convergence bound that closes this gap.
Cite
@article{arxiv.2307.06644,
title = {An Improved Uniform Convergence Bound with Fat-Shattering Dimension},
author = {Roberto Colomboni and Emmanuel Esposito and Andrea Paudice},
journal= {arXiv preprint arXiv:2307.06644},
year = {2023}
}