Login / Signup
On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks.
Umut Simsekli
Mert Gürbüzbalaban
Thanh Huy Nguyen
Gaël Richard
Levent Sagun
Published in:
CoRR (2019)
Keyphrases
</>
heavy tailed
stochastic gradient descent
matrix factorization
generalized gaussian
step size
least squares
incremental learning
machine learning
image sequences
loss function