For HyperBFs AGOP is a greedy approximation to gradient descent

Abstract

The Average Gradient Outer Product (AGOP) provides a novel approach to feature learning in neural networks. We applied both AGOP and Gradient Descent to learn the matrix M in the Hyper Basis Function Network (HyperBF) and observed very similar performance. We show formally that AGOP is a greedy approximation of gradient descent.