1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs
Lists
Only you see this
BibTeX
@inproceedings{seide2014bit,
author = {Frank Seide and Hao Fu and Jasha Droppo and Gang Li and Dong Yu},
title = {{1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs}},
booktitle = {Interspeech},
year = {2014},
doi = {10.21437/interspeech.2014-274},
}Loading related content...