@article{learningontransformersisprovablelowrank,
  title = {Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysis},
  author = {Hongkang Li and Meng Wang and Shuai Zhang and Sijia Liu and Pin-Yu Chen},
  year = {2024},
  eprint = {2406.17167},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.17167v1},
}