Nonparametric regression with modified ReLU networks

Abstract: We consider regression estimation with modified ReLU neural networks in which network weight matrices are first modified by a function

a l p h a

before being multiplied by input vectors. We give an example of continuous, piecewise linear function

a l p h a

for which the empirical risk minimizers over the classes of modified ReLU networks with

l_{1}

and squared

l_{2}

penalties attain, up to a logarithmic factor, the minimax rate of prediction of unknown

-smooth function.

This page was built for publication: Nonparametric regression with modified ReLU networks