@article{trainingnonlineartransformersforefficien, title = {How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?}, author = {Hongkang Li and Meng Wang and Songtao Lu and Xiaodong Cui and Pin-Yu Chen}, year = {2024}, eprint = {2402.15607}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.15607v3}, }