@article{
mwigo2026generalization,
title={Generalization Bound for a Shallow Transformer Trained Using Gradient Descent},
author={Brian Mwigo and Anirban Dasgupta},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2026},
url={https://openreview.net/forum?id=t3iUeMOT8Z},
note={}
}