A closer look at covering number bounds for Gaussian kernels
Lists
Only you see this
Abstract
We establish some new bounds on the log-covering numbers of (anisotropic) Gaussian reproducing kernel Hilbert spaces. Unlike previous results in this direction we focus on small explicit constants and their dependency on crucial parameters such as the kernel bandwidth and the size and dimension of the underlying space.
BibTeX
@article{steinwart2021closer,
author = {Ingo Steinwart and Simon Fischer},
title = {{A closer look at covering number bounds for Gaussian kernels}},
journal = {J. Complex.},
year = {2021},
doi = {10.1016/j.jco.2020.101513},
}| Optimal regression rates for SVMs using Gaussian kernels | Electronic · 2013 |
| Approximation beats concentration? An approximation view on inference with smooth radial kernels | COLT · 2018 |
| Optimal Learning with Anisotropic Gaussian SVMs | arXiv · 2018 |
| Nearly-tight Bounds for Deep Kernel Learning | ICML · 2023 |
| Local Rademacher complexity bounds based on covering numbers | arXiv · 2015 |
| Fast rates for support vector machines using Gaussian kernels | The Annals of Statistics · 2007 |