Ginsburg et al. "Training Deep Networks with Stochastic Gradient Normalized by Layerwise Adaptive Second Moments." International Conference on Learning Representations, 2020.
Markdown
[Ginsburg et al. "Training Deep Networks with Stochastic Gradient Normalized by Layerwise Adaptive Second Moments." International Conference on Learning Representations, 2020.](https://mlanthology.org/iclr/2020/ginsburg2020iclr-training/)
BibTeX
@inproceedings{ginsburg2020iclr-training,
title = {{Training Deep Networks with Stochastic Gradient Normalized by Layerwise Adaptive Second Moments}},
author = {Ginsburg, Boris and Castonguay, Patrice and Hrinchuk, Oleksii and Kuchaiev, Oleksii and Lavrukhin, Vitaly and Leary, Ryan and Li, Jason and Nguyen, Huyen and Zhang, Yang and Cohen, Jonathan M.},
booktitle = {International Conference on Learning Representations},
year = {2020},
url = {https://mlanthology.org/iclr/2020/ginsburg2020iclr-training/}
}