Login / Signup
Linear Convergence of Gradient Descent For Finite Width Over-parametrized Linear Networks With General Initialization.
Ziqing Xu
Hancheng Min
Salma Tarmoun
Enrique Mallada
René Vidal
Published in:
AISTATS (2023)
Keyphrases
</>
finite dimensional
special case
nonlinear functions
data sets
neural network
logic programs
closely related
closed form
convergence rate
heterogeneous networks