Lipschitz regularized Deep Neural Networks generalize

ICLR 2019  ·  Adam M. Oberman, Jeff Calder ·

We show that if the usual training loss is augmented by a Lipschitz regularization term, then the networks generalize. We prove generalization by first establishing a stronger convergence result, along with a rate of convergence. A second result resolves a question posed in Zhang et al. (2016): how can a model distinguish between the case of clean labels, and randomized labels? Our answer is that Lipschitz regularization using the Lipschitz constant of the clean data makes this distinction. In this case, the model learns a different function which we hypothesize correctly fails to learn the dirty labels.

PDF Abstract
No code implementations yet. Submit your code now

Tasks


Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here