@article{sparsebackpropagationformoetraining, title = {Sparse Backpropagation for MoE Training}, author = {Liyuan Liu and Jianfeng Gao and Weizhu Chen}, year = {2023}, eprint = {2310.00811}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2310.00811v1}, }