Generalization Bounds for Transformer-Based Next-Token Prediction in a Language Model

MaRDI QIDQ7264948arXivFDO

Authors Insung Kong, Niklas Dexheimer, Johannes Schmidt-Hieber

Publication date 2026

Published in arXiv

arXiv classification

math.ST

This page was built for publication: Generalization Bounds for Transformer-Based Next-Token Prediction in a Language Model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7264948)