Variance Reduction in SGD by Distributed Importance Sampling

Guillaume Alain, Alex Lamb, Chinnadhurai Sankar, Aaron Courville, Yoshua Bengio

CMT Id: 96

Abstract:

Humans are able to accelerate their learning by selecting training
materials that are the most informative and at the appropriate level of
difficulty. We propose a framework for distributing deep learning in which
one set of workers search for the most informative examples in parallel
while a single worker updates the model on examples selected by importance
sampling. This leads the model to update using an unbiased estimate of the
gradient which also has minimum variance when the sampling proposal is
proportional to the L2-norm of the gradient. We show experimentally that
this method reduces gradient variance even in a context where the cost of
synchronization across machines cannot be ignored, and where the factors
for importance sampling are not updated instantly across the training set.

Conflicts: umontreal.ca