@article{adaptivebatchsizeschedulesfordistributed,
  title = {Adaptive Batch Size Schedules for Distributed Training of Language Models with Data and Model Parallelism},
  author = {Tim Tsz-Kit Lau and Weijian Li and Chenwei Xu and Han Liu and Mladen Kolar},
  year = {2024},
  eprint = {2412.21124},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.21124v2},
}