Stability and optimality in stochastic gradient descent.

Panos Toulis Dustin Tran Edoardo M. Airoldi

Published in: CoRR (2015)

Keyphrases

stochastic gradient descent
least squares
loss function
matrix factorization
step size
random forests
regularization parameter
online algorithms
multiple kernel learning
weight vector
support vector machine
optimal solution
knn
semi supervised
small number
markov random field
image processing
training data