Iterate Averaging as Regularization for Stochastic Gradient Descent.

Gergely Neu Lorenzo Rosasco

Published in: COLT (2018)

Keyphrases

stochastic gradient descent
least squares
loss function
matrix factorization
regularization parameter
step size
early stopping
random forests
support vector machine
multiple kernel learning
image restoration
importance sampling
weight vector
online algorithms
pairwise
maximum a posteriori
collaborative filtering