@article{canloopedtransformerslearntoimplement, title = {Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?}, author = {Khashayar Gatmiry and Nikunj Saunshi and Sashank J. Reddi and Stefanie Jegelka and Sanjiv Kumar}, year = {2024}, eprint = {2410.08292}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.08292v1}, }