Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models

by   Beidi Chen, et al.

Overparameterized neural networks generalize well but are expensive to train. Ideally, one would like to reduce their computational cost while retaining their generalization benefits. Sparse model training is a simple and promising approach to achieve this, but there remain challenges as existing methods struggle with accuracy loss, slow training runtime, or difficulty in sparsifying all model components. The core problem is that searching for a sparsity mask over a discrete set of sparse matrices is difficult and expensive. To address this, our main insight is to optimize over a continuous superset of sparse matrices with a fixed structure known as products of butterfly matrices. As butterfly matrices are not hardware efficient, we propose simple variants of butterfly (block and flat) to take advantage of modern hardware. Our method (Pixelated Butterfly) uses a simple fixed sparsity pattern based on flat block butterfly and low-rank matrices to sparsify most network layers (e.g., attention, MLP). We empirically validate that Pixelated Butterfly is 3x faster than butterfly and speeds up training to achieve favorable accuracy–efficiency tradeoffs. On the ImageNet classification and WikiText-103 language modeling tasks, our sparse models train up to 2.5x faster than the dense MLP-Mixer, Vision Transformer, and GPT-2 medium with no drop in accuracy.


page 1

page 2

page 3

page 4


ViTALiTy: Unifying Low-rank and Sparse Approximation for Vision Transformer Acceleration with a Linear Taylor Attention

Vision Transformer (ViT) has emerged as a competitive alternative to con...

Scatterbrain: Unifying Sparse and Low-rank Attention Approximation

Recent advances in efficient Transformers have exploited either the spar...

Sparse Iso-FLOP Transformations for Maximizing Training Efficiency

Recent works have explored the use of weight sparsity to improve the tra...

Accurate Neural Network Pruning Requires Rethinking Sparse Optimization

Obtaining versions of deep neural networks that are both highly-accurate...

projUNN: efficient method for training deep networks with unitary matrices

In learning with recurrent or very deep feed-forward networks, employing...

Ramanujan Bipartite Graph Products for Efficient Block Sparse Neural Networks

Sparse neural networks are shown to give accurate predictions competitiv...

Spartan: Differentiable Sparsity via Regularized Transportation

We present Spartan, a method for training sparse neural network models w...

Please sign up or login with your details

Forgot password? Click here to reset