1
AMUSE: Anytime Muon with Stable Gradient Evaluation
Muon优化器新变体AMUSE，实现任意时刻稳定梯度评估，41页论文含25图详解算法改进。
arXiv:2605.22432v1 Announce Type: new Abstract: Modern deep learning commonly relies on AdamW with prescribed learning rate schedules, but recent work…