On Symmetry and Initialization for Neural Networks

Ido Nachum, Amir Yehudayoff

Keywords: Neural Network Theory, Symmetry

TL;DR: When initialized properly, neural networks can learn the simple class of symmetric functions; when initialized randomly, they fail.

Abstract: This work provides an additional step in the theoretical understanding of neural networks. We consider neural networks with one hidden layer and show that when learning symmetric functions, one can choose initial conditions so that standard SGD training efficiently produces generalization guarantees. We empirically verify this and show that this does not hold when the initial conditions are chosen at random. The proof of convergence investigates the interaction between the two layers of the network. Our results highlight the importance of using symmetry in the design of neural networks.