# SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training

arXiv: https://arxiv.org/abs/2101.01163 · HTML: https://mlsanity.com/paper/2101.01163/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 49 of its 81 references that are in the map.
- First posted on arXiv 4 Jan 2021.

## Builds on (most cited first, 30 of 49)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [signSGD: Compressed Optimisation for Non-Convex Problems](https://mlsanity.com/paper/1802.04434/) (2018)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Model compression via distillation and quantization](https://mlsanity.com/paper/1802.05668/) (2018)
- [The Lottery Ticket Hypothesis for Pre-trained BERT Networks](https://mlsanity.com/paper/2007.12223/) (2020)
- [Tensorizing Neural Networks](https://mlsanity.com/paper/1509.06569/) (2015)
- [Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks](https://mlsanity.com/paper/1908.05033/) (2019)
- [Compressing Deep Convolutional Networks using Vector Quantization](https://mlsanity.com/paper/1412.6115/) (2014)
- [Training Deep Neural Networks with 8-bit Floating Point Numbers](https://mlsanity.com/paper/1812.08011/) (2018)
- [Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks](https://mlsanity.com/paper/1909.11957/) (2019)
- [Scalable Methods for 8-bit Training of Neural Networks](https://mlsanity.com/paper/1805.11046/) (2018)
- [SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks](https://mlsanity.com/paper/1708.04485/) (2017)
- [Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning](https://mlsanity.com/paper/1611.05128/) (2016)

## Abstract (arXiv)

The record-breaking performance of deep neural networks (DNNs) comes with heavy parameterization, leading to external dynamic random-access memory (DRAM) for storage. The prohibitive energy of DRAM accesses makes it non-trivial to deploy DNN on resource-constrained devices, calling for minimizing the weight and data movements to improve the energy efficiency. We present SmartDeal (SD), an algorithm framework to trade higher-cost memory storage/access for lower-cost computation, in order to aggressively boost the storage and energy efficiency, for both inference and training. The core of SD is a novel weight decomposition with structural constraints, carefully crafted to unleash the hardware efficiency potential. Specifically, we decompose each weight tensor as the product of a small basis matrix and a large structurally sparse coefficient matrix whose non-zeros are quantized to power-of-2. The resulting sparse and quantized DNNs enjoy greatly reduced energy for data movement and weight storage, incurring minimal overhead to recover the original weights thanks to the sparse bit-operations and cost-favorable computations. Beyond inference, we take another leap to embrace energy-efficient training, introducing innovative techniques to address the unique roadblocks arising in training while preserving the SD structures. We also design a dedicated hardware accelerator to fully utilize the SD structure to improve the real energy efficiency and latency. We conduct experiments on both multiple tasks, models and datasets in different settings. Results show that: 1) applied to inference, SD achieves up to 2.44x energy efficiency as evaluated via real hardware implementations; 2) applied to training, SD leads to 10.56x and 4.48x reduction in the storage and training energy, with negligible accuracy loss compared to state-of-the-art training baselines. Our source codes are available online.