Skip to content (access key 's')
Logo of Technion
Logo of CS Department
Logo of CS4People

The Taub Faculty of Computer Science Events and Talks

Sparse Linear Networks with a Fixed Butterfly
event speaker icon
Omer Leibovitch (M.Sc. Thesis Seminar)
event date icon
Monday, 12.04.2021, 12:30
event location icon
Zoom Lecture: 98712430421
For password to lecture, please contact:
event speaker icon
Advisor: Prof. Nir Ailon
A butterfly network consists of logarithmically many layers, each with a linear number of pre-specified nonzero weights. We propose to replace a dense linear layer in any neural network by an architecture based on the butterfly network. The proposed architecture significantly improves upon the quadratic number of weights required in a standard dense layer to nearly linear with little compromise in expressibility of the resulting operator. In a collection of wide variety of experiments, including supervised prediction on both the NLP and vision data, we show that this not only produces results that match and often outperform existing well-known architectures, but it also offers faster training and prediction in deployment. Theoretical result presented in the paper explain why the training speed and outcome are not compromised by our proposed approach.