"Convexifying Transformers: Improving optimization and understanding of ..."

Tolga Ergen, Behnam Neyshabur, Harsh Mehta (2022)

Details and statistics

DOI: 10.48550/ARXIV.2211.11052

access: open

type: Informal or Other Publication

metadata version: 2022-11-24

a service of  Schloss Dagstuhl - Leibniz Center for Informatics