Login / Signup
The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program.
Yifei Wang
Mert Pilanci
Published in:
ICLR (2022)
Keyphrases
</>
extreme points
convex hull
convex sets
backpropagation neural network
convex optimization
finite number
infinite dimensional
geometric properties
neural network
linear program
finite dimensional