@article{understandingwarmupstabledecaylearning,
  title = {Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective},
  author = {Kaiyue Wen and Zhiyuan Li and Jason Wang and David Hall and Percy Liang and Tengyu Ma},
  year = {2024},
  eprint = {2410.05192},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.05192v3},
}