On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory

Authors

  • Alexandre Araujo Université Paris-Dauphine
  • Benjamin Negrevergne Université Paris-Dauphine
  • Yann Chevaleyre Université Paris Dauphine
  • Jamal Atif Université Paris-Dauphine

Keywords:

Adversarial Learning & Robustness

Abstract

This paper tackles the problem of Lipschitz regularization of Convolutional Neural Networks. Lipschitz regularity is now established as a key property of modern deep learning with implications in training stability, generalization, robustness against adversarial examples, etc. However, computing the exact value of the Lipschitz constant of a neural network is known to be NP-hard. Recent attempts from the literature introduce upper bounds to approximate this constant that are either efficient but loose or accurate but computationally expensive. In this work, by leveraging the theory of Toeplitz matrices, we introduce a new upper bound for convolutional layers that is both tight and easy to compute. Based on this result we devise an algorithm to train Lipschitz regularized Convolutional Neural Networks.

Downloads

Published

2021-05-18

How to Cite

Araujo, A., Negrevergne, B., Chevaleyre, Y., & Atif, J. (2021). On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory. Proceedings of the AAAI Conference on Artificial Intelligence, 35(8), 6661-6669. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16824

Issue

Section

AAAI Technical Track on Machine Learning I