@article{weightdecaymaymattermorethanmupforlearni,
  title = {Weight Decay may matter more than muP for Learning Rate Transfer in Practice},
  author = {Atli Kosson and Jeremy Welborn and Yang Liu and Martin Jaggi and Xi Chen},
  year = {2025},
  eprint = {2510.19093},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.19093},
}