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

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.

This content will become publicly available on December 9, 2025

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

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