Training Dynamics of Softmax Self-Attention: Fast Global Convergence via Preconditioning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Goel, Gautam, Soltanolkotabi, Mahdi, Bartlett, Peter
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.01514