Analytic function approximation by path norm regularized deep networks

Abstract

We show that neural networks with absolute value activation function and with the path norm, the depth, the width and the network weights having logarithmic dependence on $1/\epsilon$ can $\epsilon$-approximate functions that are analytic on certain regions of ${\mathbb{C}}^d$.

References in corpus (3)

• Nonparametric regression using deep neural networks with ReLU activation function
• Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks
• Piecewise linear activations substantially shape the loss surfaces of neural networks