1 code implementation • 19 Dec 2019 • Eric C. Cyr, Stefanie Günther, Jacob B. Schroder
This paper investigates multilevel initialization strategies for training very deep neural networks with a layer-parallel multigrid solver.
1 code implementation • 7 Aug 2017 • Jacob B. Schroder
This work considers a multigrid reduction in time (MGRIT) algorithm that is able to parallelize over the thousands of training runs and converge to the exact same solution as traditional training would provide.