Natural Gradient Descent for On-Line Learning

Natural gradient descent is an on-line variable-metric optimization algorithm which utilizes an underlying Riemannian parameter space. We analyze the dynamics of natural gradient descent beyond the asymptotic regime by employing an exact statistical mechanics description of learning in two-layer feed-forward neural networks. For a realizable learning scenario we find significant improvements over standard gradient descent for both the transient and asymptotic stages of learning, with a slower power law increase in learning time as task complexity grows.