@inproceedings{ontheconvergenceofencoderonlyshallow, title = {On the Convergence of Encoder-only Shallow Transformers}, year = {2023}, booktitle = {NeurIPS 2023 11}, eprint = {2311.01575}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2311.01575v1}, }