The Local Elasticity of Neural Networks

ICLR, 2020.

Cited by: 1|Views22
EI
Weibo:
Zhang et al observe that neural networks can perfectly fit corrupted labels while maintaining a certain amount of generalization power1. We complement this line of findings by proposing a hypothesis that fundamentally distinguishes neural networks from linear classifiers2. This h...

Abstract:

This paper presents a phenomenon in neural networks that we refer to as local elasticity. Roughly speaking, a classifier is said to be locally elastic if its prediction at a feature vector x' is not significantly perturbed, after the classifier is updated via stochastic gradient descent at a (labeled) feature vector x that is dissimilar t...More

Code:

Data:

Your rating :
0

 

Tags
Comments