"Implicit Regularization of Gradient Flow on One-Layer Softmax Attention."

Heejune Sheen et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2403.08699

access: open

type: Informal or Other Publication

metadata version: 2024-04-05

a service of  Schloss Dagstuhl - Leibniz Center for Informatics