@article{maximizingcommunicationefficiencyforlarg, title = {Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam}, author = {Yucheng Lu and Conglong Li and Minjia Zhang and Christopher De Sa and Yuxiong He}, year = {2022}, eprint = {2202.06009}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2202.06009v3}, }