Stochastic Gradient Descent: Going As Fast As Possible But Not Faster.

Alice Schoenauer Sebag Marc Schoenauer Michèle Sebag

Published in: CoRR (2017)

Keyphrases

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