Muon optimizer outperforms AdamW in ViT training on two image datasets, with gains that depend on data augmentation strength and are linked to wider singular-value spread in QKV gradients and prevention of late-training mode collapse in MLP blocks.
Beyond muon: Mud (momentum decorrelation) for faster transformer training.arXiv preprint arXiv:2603.17970, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Muon in Vision Transformers: Optimizer-Recipe Interactions and Gradient Spectra
Muon optimizer outperforms AdamW in ViT training on two image datasets, with gains that depend on data augmentation strength and are linked to wider singular-value spread in QKV gradients and prevention of late-training mode collapse in MLP blocks.