Intrinsic Dimensionality and Generalization Properties of the R-Norm Inductive Bias
Abstract
We study the structural and statistical properties of R-norm minimizing interpolants of datasets labeled by specific target functions. The R-norm is the basis of an inductive bias for two-layer neural networks, recently introduced to capture the functional effect of controlling the size of network weights, independently of the network width. We find that these interpolants are intrinsically multivariate functions, even when there are ridge functions that fit the data, and also that the R-norm inductive bias is not sufficient for achieving statistically optimal generalization for certain learning problems. Altogether, these results shed new light on an inductive bias that is connected to practical neural network training.
Cite
Text
Ardeshir et al. "Intrinsic Dimensionality and Generalization Properties of the R-Norm Inductive Bias." Conference on Learning Theory, 2023.Markdown
[Ardeshir et al. "Intrinsic Dimensionality and Generalization Properties of the R-Norm Inductive Bias." Conference on Learning Theory, 2023.](https://mlanthology.org/colt/2023/ardeshir2023colt-intrinsic/)BibTeX
@inproceedings{ardeshir2023colt-intrinsic,
title = {{Intrinsic Dimensionality and Generalization Properties of the R-Norm Inductive Bias}},
author = {Ardeshir, Navid and Hsu, Daniel J. and Sanford, Clayton H.},
booktitle = {Conference on Learning Theory},
year = {2023},
pages = {3264-3303},
volume = {195},
url = {https://mlanthology.org/colt/2023/ardeshir2023colt-intrinsic/}
}