Analysis Of Momentum Methods

Gradient descent-based optimization methods underpin the parameter training which results in the impressive results now found when testing neural networks. Introducing stochasticity is key to their success in practical problems, and there is some understanding of the role of stochastic gradient descent in this context. Momentum modifications of gradient descent such as Polyak's Heavy Ball method (HB) and Nesterov's method of accelerated gradients (NAG), are also widely adopted. In this work our focus is on understanding the role of momentum in the training of neural networks, concentrating on the common situation in which the momentum contribution is fixed at each step of the algorithm; to expose the ideas simply we work in the deterministic setting. We show that, contrary to popular belief, standard implementations of fixed momentum methods do no more than act to rescale the learning rate. We achieve this by showing that the momentum method converges to a gradient flow, with a momentum-dependent time-rescaling, using the method of modified equations from numerical analysis. Furthermore we show that the momentum method admits an exponentially attractive invariant manifold on which the dynamics reduces to a gradient flow with respect to a modified loss function, equal to the original one plus a small perturbation.