Paper ID: 2311.18022

Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training

Max Milkert, David Hyde, Forrest Laine

A neural network with ReLU activations may be viewed as a composition of piecewise linear functions. For such networks, the number of distinct linear regions expressed over the input domain has the potential to scale exponentially with depth, but it is not expected to do so when the initial parameters are chosen randomly. Therefore, randomly initialized models are often unnecessarily large, even when approximating simple functions. To address this issue, we introduce a novel training strategy: we first reparameterize the network weights in a manner that forces the network to exhibit a number of linear regions exponential in depth. Training first on our derived parameters provides an initial solution that can later be refined by directly updating the underlying model weights. This approach allows us to learn approximations of convex, one-dimensional functions that are several orders of magnitude more accurate than their randomly initialized counterparts. We further demonstrate how to extend our approach to multidimensional and non convex functions, with similar benefits observed.

Submitted: Nov 29, 2023