Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks.

Difan Zou Yuan Cao Dongruo Zhou Quanquan Gu

Published in: CoRR (2018)

Keyphrases

stochastic gradient descent
least squares
step size
loss function
matrix factorization
random forests
support vector machine
multiple kernel learning
similarity measure
linear combination
image sequences
logistic regression
importance sampling
online algorithms