MMODELYST
People/Martin Takáč
PPL

Martin Takáč

Papers (3)
LionMuon: Alternating Spectral and Sign Descent for Efficient TrainingGradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued ParametersMuon with Nesterov Momentum: Heavy-Tailed Noise and (Randomized) Inexact Polar Decomposition