@inproceedings{arda2026finite,
  title     = {Finite-Time Analysis of Gradient Descent for Shallow Transformers},
  author    = {Arda, Enes and Cayci, Semih and Eryilmaz, Atilla},
  booktitle = {Proceedings of The 29th International Conference on Artificial Intelligence and Statistics},
  pages     = {3988--3996},
  year      = {2026},
  editor    = {Khan, Emtiyaz and Li, Yingzhen and Solin, Arno and Ramdas, Aaditya},
  volume    = {300},
  series    = {Proceedings of Machine Learning Research},
  publisher = {PMLR},
  url       = {https://proceedings.mlr.press/v300/arda26a.html}
}