The Lottery Ticket Hypothesis: Finding Small, Trainable Neural Networks

03/09/2018 ∙ by Jonathan Frankle, et al. ∙ 0

Neural network compression techniques are able to reduce the parameter counts of trained networks by over 90 inference performance--without compromising accuracy. However, contemporary experience is that it is difficult to train small architectures from scratch, which would similarly improve training performance. We articulate a new conjecture to explain why it is easier to train large networks: the "lottery ticket hypothesis." It states that large networks that train successfully contain subnetworks that--when trained in isolation--converge in a comparable number of iterations to comparable accuracy. These subnetworks, which we term "winning tickets," have won the initialization lottery: their connections have initial weights that make training particularly effective. We find that a standard technique for pruning unnecessary network weights naturally uncovers a subnetwork which, at the start of training, comprised a winning ticket. We present an algorithm to identify winning tickets and a series of experiments that support the lottery ticket hypothesis. We consistently find winning tickets that are less than 20 fully-connected, convolutional, and residual architectures for MNIST and CIFAR10. Furthermore, winning tickets at moderate levels of pruning (20-50 the original network size) converge up to 6.7x faster than the original network and exhibit higher test accuracy.



There are no comments yet.


page 1

page 2

page 3

page 4

Code Repositories


Lottery Ticker Hypothesis in Chainer

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.