ARM - Augment-REINFORCE-Merge Gradient for Stochastic Binary Networks

ICLR, 2019.

Cited by: 17|Views40
EI

Abstract:

To backpropagate the gradients through stochastic binary layers, we propose the augment-REINFORCE-merge (ARM) estimator that is unbiased, exhibits low variance, and has low computational complexity. Exploiting variable augmentation, REINFORCE, and reparameterization, the ARM estimator achieves adaptive variance reduction for Monte Carlo...More

Code:

Data:

Your rating :
0

 

Tags
Comments