ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables
Lists
Only you see this
Abstract
To address the challenge of backpropagating the gradient through categorical variables, we propose the augment-REINFORCE-swap-merge (ARSM) gradient estimator that is unbiased and has low variance. ...
BibTeX
@inproceedings{yin2019arsm,
author = {Mingzhang Yin and Yuguang Yue and Mingyuan Zhou},
title = {{ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables}},
booktitle = {International Conference on Machine Learning},
year = {2019},
}