Lipschitz constant estimation for Neural Networks via sparse polynomial optimization

We introduce LiPopt, a polynomial optimization framework for computing increasingly tighter upper bounds on the Lipschitz constant of neural networks. The underlying optimization problems boil down to either linear (LP) or semidefinite (SDP) programming. We show how to use the sparse connectivity of a network, to significantly reduce the complexity of computation. This is specially useful for convolutional as well as pruned neural networks. We conduct experiments on networks with random weights as well as networks trained on MNIST, showing that in the particular case of the `1-Lipschitz constant, our approach yields superior estimates, compared to baselines available in the literature.


Presented at:
8th International Conference on Learning Representations, Addis Ababa, ETHIOPIA, April 26-30, 2020
Year:
Apr 26 2020
Keywords:
Additional link:
Laboratories:


Note: The status of this file is: Anyone


 Record created 2020-01-20, last modified 2020-10-29

Final:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)