Sigmoid Self-Attention has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yan, Fanqi, Nguyen, Huy, Akbarian, Pedram, Ho, Nhat, Rinaldo, Alessandro
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.00281