In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Ruiqi, Wu, Jingfeng, Bartlett, Peter L.
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2402.14951