@article{dasgdsqueezingsgdparallelization, title = {DaSGD: Squeezing SGD Parallelization Performance in Distributed Training Using Delayed Averaging}, author = {Qinggang Zhou and Yawen Zhang and Pengcheng Li and Xiaoyong Liu and Jun Yang and Runsheng Wang and Ru Huang}, year = {2020}, eprint = {2006.00441}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2006.00441v1}, }