
Muon and a Selective Survey on Steepest Descent in Riemannian and Non-Riemannian Manifolds
Muon from first principles, what makes it different from other optimizers, and why it works so well.
Muon from first principles, what makes it different from other optimizers, and why it works so well.
A possible reason why Muon converges faster & does better at higher learning rates than Adam.
Why Muon still work despite not perfectly semi-orthogonalizing the gradients.
Simply switching to Muon can already get you 2x efficiency gains. But you can squeeze out an extra 1-2% by optimizing the Newton-Schulz coefficients.
The CASPR optimizer, a variant of Shampoo, reduces to Muon when we remove the accumulation on the preconditioners.
Instead of asking, ‘Which optimizer should I use?’ ask, ‘In which space do my features live in?’