@article{adistributionalsimplicitybiasinthe, title = {A distributional simplicity bias in the learning dynamics of transformers}, author = {Riccardo Rende and Federica Gerace and Alessandro Laio and Sebastian Goldt}, year = {2024}, eprint = {2410.19637}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.19637v1}, }