@inproceedings{transformerslearnthroughgradualrank, title = {Transformers learn through gradual rank increase}, author = {Enric Boix-Adsera and Etai Littwin and Emmanuel Abbe and Samy Bengio and Joshua Susskind}, year = {2023}, booktitle = {NeurIPS 2023 11}, eprint = {2306.07042}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2306.07042v2}, }