Sparse Linear Networks with a Fixed Butterfly Structure: Theory and Practice

Nir Ailon, Omer Leibovitch, Vineet Sreedharan Nair

Keywords: Butterfly Network, Matrix approximation, Encoder-Decoder Network, Optimization Landscape

Abstract: A butterfly network consists of logarithmically many layers, each with a linear number of non-zero weights (pre-specified). The fast Johnson-Lindenstrauss transform (FJLT) can be represented as a butterfly network followed by a random projection to a subset of the coordinates. Moreover, a random matrix based on FJLT with high probability approximates the action of any matrix on a vector. Motivated by these facts, 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. To understand the optimization problems posed by neural networks with a butterfly network, we study the optimization landscape of the encoder-decoder network, where the encoder is replaced by a butterfly network followed by a dense linear layer in smaller dimension. Theoretical result presented in the paper explain why the training speed and outcome are not compromised by our proposed approach. Empirically we demonstrate that the network performs as well as the encoder-decoder network.

One-sentence Summary: Replacing a dense linear layer in any neural network with an architecture based on butterfly network.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=23XnhAAIVw