Deep Learning Generalization, Extrapolation, and Over-parameterization

Abstract: We study the generalization of over-parameterized deep networks (for image classification) in relation to the convex hull of their training sets. Despite their great success, generalization of deep networks is considered a mystery. These models have orders of magnitude more parameters than their training samples, and they can achieve perfect accuracy on their training sets, even when training images are randomly labeled, or the contents of images are replaced with random noise. The training loss function of these models has infinite number of near zero minimizers, where only a small subset of those minimizers generalize well. Overall, it is not clear why models need to be over-parameterized, why we should use a very specific training regime to train them, and why their classifications are so susceptible to imperceivable adversarial perturbations (phenomenon known as adversarial vulnerability) \cite{papernot2016limitations,shafahi2018adversarial,tsipras2018robustness}. Some recent studies have made advances in answering these questions, however, they only consider interpolation. We show that interpolation is not adequate to understand generalization of deep networks and we should broaden our perspective.