Author name: Da Chang, Qiankun Shi, Lvgang Zhang, Yu Li, Ruijie Zhang, Yao Lu, Yongxiang Liu, Ganzhao Yuan

arXiv:2603.28254v2 Announce Type: replace-cross
Abstract: Orthogonalized-update optimizers such as Muon improve training of matrix-valued parameters, but existing extensions typically either rescale updates after orthogonalization or use heavier white…

arXiv:2603.28254v1 Announce Type: new
Abstract: Orthogonalized-update optimizers such as Muon improve training of matrix-valued parameters, but existing extensions mostly act either after orthogonalization by rescaling updates or before it with heavie…