The Generalization Error of the Minimum-norm Solutions for Over-parameterized Neural Networks
Machine Learning
2021-01-29 v2 Machine Learning
Statistics Theory
Statistics Theory
Abstract
We study the generalization properties of minimum-norm solutions for three over-parametrized machine learning models including the random feature model, the two-layer neural network model and the residual network model. We proved that for all three models, the generalization error for the minimum-norm solution is comparable to the Monte Carlo rate, up to some logarithmic terms, as long as the models are sufficiently over-parametrized.
Cite
@article{arxiv.1912.06987,
title = {The Generalization Error of the Minimum-norm Solutions for Over-parameterized Neural Networks},
author = {Weinan E and Chao Ma and Lei Wu},
journal= {arXiv preprint arXiv:1912.06987},
year = {2021}
}
Comments
Published version