Scaling transition from momentum stochastic gradient descent to plain stochastic gradient descent.

Kun Zeng Jinlan Liu Zhixia Jiang Dongpo Xu

Published in: CoRR (2021)

Keyphrases

stochastic gradient descent
least squares
loss function
matrix factorization
random forests
step size
weight vector
support vector machine
regularization parameter
learning rate
importance sampling
multiple kernel learning
online algorithms
closed form
collaborative filtering
image processing
upper bound