Author

Emanuele Zangrando

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

Stiefel-AdamW: Geometry-Aware AdamW for Linear Factorization Blocks

Stiefel-AdamW is introduced, a near drop-in replacement for AdamW for use wherever such blocks appear, and it is shown that the resulting optimizer inherits both the stability benefits of Riemannian methods and standard convergence guarantees.

Emanuele Zangrando, M. Sutti, Francesco Tudisco · 0 citations