Muon does not converge on convex Lipschitz functions regardless of learning rate, while error feedback restores theoretical convergence but degrades performance on CIFAR-10 and nanoGPT tasks.
and Blondel, Mathieu and Gazagnadou, Nidham and Pedregosa, Fabian , title =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Proposes Polyak schedulers for SAM with convergence proofs in deterministic and stochastic settings and empirical results showing reduced tuning needs.
citing papers explorer
-
Muon Does Not Converge on Convex Lipschitz Functions
Muon does not converge on convex Lipschitz functions regardless of learning rate, while error feedback restores theoretical convergence but degrades performance on CIFAR-10 and nanoGPT tasks.
-
Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler
Proposes Polyak schedulers for SAM with convergence proofs in deterministic and stochastic settings and empirical results showing reduced tuning needs.