Data-dependent Pruning to find the Winning Lottery Ticket
share
The Lottery Ticket Hypothesis postulates that a freshly initialized neural network contains a small subnetwork that can be trained in isolation to achieve similar performance as the full network. Our paper examines several alternatives to search for such subnetworks. We conclude that incorporating a data dependent component into the pruning criterion in the form of the gradient of the training loss – as done in the SNIP method – consistently improves the performance of existing pruning algorithms.
READ FULL TEXT