Home Page




Editorial Board

Special Issues

Open Source Software

Proceedings (PMLR)

Data (DMLR)

Transactions (TMLR)




Frequently Asked Questions

Contact Us

RSS Feed

Optimal Bump Functions for Shallow ReLU networks: Weight Decay, Depth Separation, Curse of Dimensionality

Stephan Wojtowytsch; 25(27):1−49, 2024.


In this note, we study how neural networks with a single hidden layer and ReLU activation interpolate data drawn from a radially symmetric distribution with target labels 1 at the origin and 0 outside the unit ball, if no labels are known inside the unit ball. With weight decay regularization and in the infinite neuron, infinite data limit, we prove that a unique radially symmetric minimizer exists, whose average parameters and Lipschitz constant grow as $d$ and $\sqrt{d}$ respectively. We furthermore show that the average weight variable grows exponentially in $d$ if the label $1$ is imposed on a ball of radius $\varepsilon$ rather than just at the origin. By comparison, a neural networks with two hidden layers can approximate the target function without encountering the curse of dimensionality.

© JMLR 2024. (edit, beta)