Seminar · Recording · Feb 6, 2026
The Polar Express: Optimal Matrix Sign Methods and Their Application to the Muon Algorithm
Robert Gower, Flatiron Institute
More on bfloat16 and matrix sign function
We use cookies for analytics.
Seminar, Hosted by Princeton University
New York University
David Persson presents Polar Express, a method for polar decomposition and the matrix sign function motivated by the Muon neural-network optimizer. It uses matrix multiplications suited to GPUs and adapts each polynomial update through a minimax problem to reduce worst-case error. The talk covers convergence, finite-precision implementation in bfloat16 and validation-loss improvements when training GPT-2 on FineWeb data. This is an in-person PACM IDeAS seminar at Princeton.
Seminar · Recording · Feb 6, 2026
Robert Gower, Flatiron Institute