Tight analyses for non-smooth stochastic gradient descent.

Nicholas J. A. Harvey Christopher Liaw Yaniv Plan Sikander Randhawa

Published in: COLT (2019)

Keyphrases

stochastic gradient descent
least squares
loss function
matrix factorization
step size
lower bound
random forests
upper bound
worst case
online algorithms
support vector machine
multiple kernel learning
regularization parameter
decision trees
monte carlo
logistic regression
benchmark datasets
image processing