Back to Search Start Over

Universality Laws for High-Dimensional Learning with Random Features

Authors :
Hu, Hong
Lu, Yue M.
Publication Year :
2020

Abstract

We prove a universality theorem for learning with random features. Our result shows that, in terms of training and generalization errors, a random feature model with a nonlinear activation function is asymptotically equivalent to a surrogate linear Gaussian model with a matching covariance matrix. This settles a so-called Gaussian equivalence conjecture based on which several recent papers develop their results. Our method for proving the universality theorem builds on the classical Lindeberg approach. Major ingredients of the proof include a leave-one-out analysis for the optimization problem associated with the training process and a central limit theorem, obtained via Stein's method, for weakly correlated random variables.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2009.07669
Document Type :
Working Paper