@article{trainingdiagonallinearnetworkswith,
  title = {Training Diagonal Linear Networks with Stochastic Sharpness-Aware Minimization},
  author = {Gabriel Clara and Sophie Langer and Johannes Schmidt-Hieber},
  year = {2025},
  eprint = {2503.11891},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.11891v1},
}