Number of items: 2.
Conference or Workshop Item (A Paper)
Mohtashami, Amirkeivan and Jaggi, Martin and Stich, Sebastian U.
(2023)
Special Properties of Gradient Descent with Large Learning Rates.
Mohtashami, Amirkeivan and Jaggi, Martin and Stich, Sebastian U.
(2022)
Masked Training of Neural Networks with Partial Gradients.
(In Press)
This list was generated on Thu Nov 21 13:18:44 2024 CET.