On the Generalization Properties of Minimum-norm Solutions for Over-parameterized Neural Network Models

12/15/2019

∙

by   Weinan E, et al.

∙

10

∙

share

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.