Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Hongkang, Lu, Songtao, Chen, Pin-Yu, Cui, Xiaodong, Wang, Meng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!