A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case
Abstract
We give a tight characterization of the (vectorized Euclidean) norm of weights required to realize a function $f:\mathbb{R}\rightarrow \mathbb{R}^d$ as a single hidden-layer ReLU network with an unbounded number of units (infinite width), extending the univariate characterization of Savarese et al. (2019) to the multivariate case.
Cite
Text
Ongie et al. "A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case." International Conference on Learning Representations, 2020.Markdown
[Ongie et al. "A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case." International Conference on Learning Representations, 2020.](https://mlanthology.org/iclr/2020/ongie2020iclr-function/)BibTeX
@inproceedings{ongie2020iclr-function,
title = {{A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case}},
author = {Ongie, Greg and Willett, Rebecca and Soudry, Daniel and Srebro, Nathan},
booktitle = {International Conference on Learning Representations},
year = {2020},
url = {https://mlanthology.org/iclr/2020/ongie2020iclr-function/}
}