@article{scalingdistributedtrainingwithadaptive, title = {Scaling Distributed Training with Adaptive Summation}, author = {Saeed Maleki and Madan Musuvathi and Todd Mytkowicz and Olli Saarikivi and Tianju Xu and Vadim Eksarevskiy and Jaliya Ekanayake and Emad Barsoum}, year = {2020}, eprint = {2006.02924}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2006.02924v1}, }