papers AI Learner
The Github is limit! Click to go to the new site.

Are All Layers Created Equal?

2019-02-06
Chiyuan Zhang, Samy Bengio, Yoram Singer

Abstract

Understanding learning and generalization of deep architectures has been a major research objective in the recent years with notable theoretical progress. A main focal point of generalization studies stems from the success of excessively large networks which defy the classical wisdom of uniform convergence and learnability. We study empirically the layer-wise functional structure of over-parameterized deep models. We provide evidence for the heterogeneous characteristic of layers. To do so, we introduce the notion of (post training) re-initialization and re-randomization robustness. We show that layers can be categorized into either “robust” or “critical”. In contrast to critical layers, resetting the robust layers to their initial value has no negative consequence, and in many cases they barely change throughout training. Our study provides further evidence that mere parameter counting or norm accounting is too coarse in studying generalization of deep models.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.01996

PDF

http://arxiv.org/pdf/1902.01996


Similar Posts

Comments