Efficient Proximal Mapping of the 1-path-norm of Shallow Networks

07/02/2020 ∙ by Fabian Latorre, et al. ∙ 0

We demonstrate two new important properties of the 1-path-norm of shallow neural networks. First, despite its non-smoothness and non-convexity it allows a closed form proximal operator which can be efficiently computed, allowing the use of stochastic proximal-gradient-type methods for regularized empirical risk minimization. Second, when the activation functions is differentiable, it provides an upper bound on the Lipschitz constant of the network. Such bound is tighter than the trivial layer-wise product of Lipschitz constants, motivating its use for training networks robust to adversarial perturbations. In practical experiments we illustrate the advantages of using the proximal mapping and we compare the robustness-accuracy trade-off induced by the 1-path-norm, L1-norm and layer-wise constraints on the Lipschitz constant (Parseval networks).

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 27

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.