Linear Convergence of Gradient Descent For Finite Width Over-parametrized Linear Networks With General Initialization.
Ziqing Xu, Hancheng Min, Salma Tarmoun, Enrique Mallada, Ren Vidal
Browse the full AISTATS paper archive.
Ziqing Xu, Hancheng Min, Salma Tarmoun, Enrique Mallada, Ren Vidal
Browse the full AISTATS paper archive.