Strobl24

More on Harmonic Analysis

June 9th - 15th 2024

Strobl, AUSTRIA

"A multivariate Riesz basis of ReLU neural networks"

Vybiral, Jan

We consider the trigonometric-like system of piecewise linear functions introduced recently by Daubechies, DeVore, Foucart, Hanin, and Petrova. We provide an alternative proof that this system forms a Riesz basis of L2([0,1]) based on the Gershgorin theorem. We also generalize this system to higher dimensions d>1 by a construction, which avoids using (tensor) products. As a consequence, the functions from the new Riesz basis of L2([0,1]^d) can be easily represented by neural networks. Moreover, the Riesz constants of this system are independent of d, making it an attractive building block regarding future multivariate analysis of neural networks. This is a joint work with Cornelia Schneider (University of Erlangen).

« back