Linear-Size Neural Network Representation of Piecewise Affine Functions in ${\mathbb{R}}^2$

Abstract

It is shown that any continuous piecewise affine (CPA) function ${\mathbb{R}}^2\to \mathbb{R}$ with $p$ pieces can be represented by a ReLU neural network with two hidden layers and $O(p)$ neurons. Unlike prior work, which focused on convex pieces, this analysis considers CPA functions with connected but potentially non-convex pieces.