The Generalization Error of the Minimum-norm Solutions for Over-parameterized Neural Networks
From MaRDI portal
Publication:6331128
zbMATH Open1524.68273arXiv1912.06987MaRDI QIDQ6331128FDOQ6331128
Publication date: 15 December 2019
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.
General nonlinear regression (62J02) Learning and adaptive systems in artificial intelligence (68T05) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22)
This page was built for publication: The Generalization Error of the Minimum-norm Solutions for Over-parameterized Neural Networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6331128)
