Cogradient Descent for Bilinear Optimization

Cited by: 0|Bibtex|Views56|Links

Abstract:

Conventional learning methods simplify the bilinear model by regarding two intrinsically coupled factors independently, which degrades the optimization procedure. One reason lies in the insufficient training due to the asynchronous gradient descent, which results in vanishing gradients for the coupled variables. In this paper, we introd...More

Code:

Data:

Your rating :
0

 

Tags
Comments