Skip to content

Author

Issei Sato

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.

#artificial intelligence Preprint Jan 2025

Gradient Heterogeneity Complements Hessian Heterogeneity in Transformer Optimization

This study provides a theoretical analysis showing that gradient heterogeneity, together with Hessian heterogeneity, degrades the convergence of gradient-based methods such as SGD, while sign-based methods are substantially less sensitive to this effect.

Akiyoshi Tomihari, Issei Sato · 6 citations · ⚡1