ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables

Mingzhang Yin, Yuguang Yue, Mingyuan Zhou

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},
}
Figure