RNN Training along Locally Optimal Trajectoriesvia Frank-Wolfe Algorithm

ICPR, pp. 10532-10539, 2020.

Cited by: 0|Views9
EI

Abstract:

We propose a novel and efficient training method for RNNs by iteratively seeking a local minima on the loss surface within a small region, and leverage this directional vector for the update, in an outer-loop. We propose to utilize the Frank-Wolfe (FW) algorithm in this context. Although, FW implicitly involves normalized gradients, whi...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments