On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Bingrui, Huang, Wei, Han, Andi, Zhou, Zhanpeng, Suzuki, Taiji, Zhu, Jun, Chen, Jianfei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!