Scaling up stochastic gradient descent for non-convex optimisation.

Saad Mohamad Hamad Alamri Abdelhamid Bouchachia

Published in: Mach. Learn. (2022)

Keyphrases

stochastic gradient descent
convex optimisation
least squares
matrix factorization
loss function
step size
weight vector
regularization parameter
multiple kernel learning
support vector machine
convergence speed
collaborative filtering