Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks.

Hristo Papazov Scott Pesme Nicolas Flammarion

Published in: AISTATS (2024)

Keyphrases

training set
training process
echo state networks
social networks
supervised learning
training phase
active learning
heterogeneous networks
learning rate
training examples
computer networks
network design
optimal control
recurrent networks
training algorithm
data sets
test set
neural network