Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Chenyang, Zhao, Qingyue, Gu, Quanquan, Cao, Yuan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!