"In-Context Learning of a Linear Transformer Block: Benefits of the MLP ..."

Ruiqi Zhang, Jingfeng Wu, Peter L. Bartlett (2024)

Details and statistics

DOI: 10.48550/ARXIV.2402.14951

access: open

type: Informal or Other Publication

metadata version: 2024-03-22

a service of  Schloss Dagstuhl - Leibniz Center for Informatics