Non-asymptotic Convergence of Training Transformers for Next-token Prediction | NSF Public Access Repository

skip to main content

An official website of the United States government Here's how you know

Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Citation Details

Non-asymptotic Convergence of Training Transformers for Next-token Prediction

Award ID(s):: 1956276 2133170 2531023

PAR ID:: 10631665

Author(s) / Creator(s):: Huang, R; Liang, Y; Yang, J

Publisher / Repository:: The Thirty-Ninth Annual Conference on Neural Information Processing Systems

Date Published:: 2024-12-09

Format(s):: Medium: X

Sponsoring Org:: National Science Foundation

Free Publicly Accessible Full Text
Accepted Manuscript
Conference Paper:
The DOI is not currently available.