"The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks."

Can Yaras et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2306.01154

access: open

type: Informal or Other Publication

metadata version: 2023-06-12

a service of  Schloss Dagstuhl - Leibniz Center for Informatics