Sparse Iso-FLOP Transformations for Maximizing Training Efficiency

Vithursan Thangarasa, Shreyas Saxena, Abhay Gupta, Sean Lie

Keywords: sparsity, sparse training, efficient deep learning, efficient computations

TL;DR: We introduce a family of Sparse Iso-FLOP Transformations which can be used as drop-in replacements for dense layers to improve their modeling capacity and FLOP efficiency. We obtain significant wins across both CV and NLP domains.

Abstract:

Recent works have explored the use of weight sparsity to improve the training
efficiency (test accuracy w.r.t training FLOPs) of deep neural networks (DNNs).
These works aim to reduce training FLOPs but training with sparse weights often
leads to accuracy loss or requires longer training schedules, making the
resulting training efficiency less clear. In contrast, we focus on using
sparsity to increase accuracy while using the same FLOPS as the dense model and
show training efficiency gains through higher accuracy. In this work, we
introduce Sparse-IFT, a family of Sparse Iso-FLOP Transformations which are used
as drop-in replacements for dense layers to improve their representational
capacity and FLOP efficiency. Each transformation is parameterized by a single
hyperparameter (sparsity level) and provides a larger search space to find
optimal sparse masks. Without changing any training hyperparameters, replacing
dense layers with Sparse-IFT leads to significant improvements across computer
vision and natural language processing tasks, including ResNet-18 on
ImageNet (+3.5\%) and GPT-3 Small on WikiText-103 (-0.4 PPL), both matching
larger dense model variants that use 2x or more FLOPs. To our knowledge, this is
the first work to demonstrate the use of sparsity for improving the accuracy of
dense models via a simple set of sparse transformations. Code is available at: https://github.com/CerebrasResearch/Sparse-IFT.

Submission Number: 41