Dmitry Chistikov

Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs

We prove that, for the fundamental regression task of learning a single neuron, training a one-hidden layer ReLU network of any width by gradient flow from a small initialisation converges to zero loss and is implicitly biased to minimise the rank of network parameters. By assuming that the trainin…