papers AI Learner
The Github is limit! Click to go to the new site.

L2-Nonexpansive Neural Networks

2019-02-06
Haifeng Qian, Mark N. Wegman

Abstract

This paper proposes a class of well-conditioned neural networks in which a unit amount of change in the inputs causes at most a unit amount of change in the outputs or any of the internal layers. We develop the known methodology of controlling Lipschitz constants to realize its full potential in maximizing robustness, with a new regularization scheme for linear layers, new ways to adapt nonlinearities and a new loss function. With MNIST and CIFAR-10 classifiers, we demonstrate a number of advantages. Without needing any adversarial training, the proposed classifiers exceed the state of the art in robustness against white-box L2-bounded adversarial attacks. They generalize better than ordinary networks from noisy data with partially random labels. Their outputs are quantitatively meaningful and indicate levels of confidence and generalization, among other desirable properties.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1802.07896

PDF

http://arxiv.org/pdf/1802.07896


Similar Posts

Comments