@article{transformersaredeepoptimizersprovablein, title = {Transformers are Deep Optimizers: Provable In-Context Learning for Deep Model Training}, author = {Weimin Wu and Maojiang Su and Jerry Yao-Chieh Hu and Zhao Song and Han Liu}, year = {2024}, eprint = {2411.16549}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.16549v1}, }