New Insight into Hybrid Stochastic Gradient Descent: Beyond With-Replacement Sampling and Convexity.

Pan Zhou Xiaotong Yuan Jiashi Feng

Published in: NeurIPS (2018)

Keyphrases

stochastic gradient descent
least squares
importance sampling
loss function
matrix factorization
step size
monte carlo
random forests
online algorithms
random sampling
regularization parameter
weight vector
support vector machine
multiple kernel learning
sample size
convex hull