Data-dependent Pruning to find the Winning Lottery Ticket

Dániel Lévai, Zsolt Zombori

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.

Knowledge Graph

arrow_drop_up

Comments

Sign up or login to leave a comment