Understanding Generalization in Recurrent Neural Networks

ICLR, 2020.

Cited by: 2|Views13
EI
Weibo:
We propose a new generalization bound for Recurrent Neural network in terms of matrix 1-norm and Fisher-Rao norm, which has no explicit dependence on the size of networks

Abstract:

In this work, we develop the theory for analyzing the generalization performance of recurrent neural networks. We first present a new generalization bound for recurrent neural networks based on matrix 1-norm and Fisher-Rao norm. The definition of Fisher-Rao norm relies on a structural lemma about the gradient of RNNs. This new generalizat...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments