Gradient Flow Structure and Quantitative Dynamics of Multi-Head Self-Attention

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Pendharkar, Ayan
Format:	Preprint
Published:	2026
Subjects:	Machine Learning 68T07, 35Q89, 37N40 I.2.6; G.2.1; F.2.0
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.04279