mlsanityData to 14 Oct 2026

A Closer Look at Hardware-Friendly Weight Quantization

arXiv 2210.03671 ↗First posted 7 Oct 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Quantizing a Deep Neural Network (DNN) model to be used on a custom accelerator with efficient fixed-point hardware implementations, requires satisfying many stringent hardware-friendly quantization constraints to train the model. We evaluate the two main classes of hardware-friendly quantization methods in the context of weight quantization: the traditional Mean Squared Quantization Error (MSQE)-based methods and the more recent gradient-based methods. We study the two methods on MobileNetV1 and MobileNetV2 using multiple empirical metrics to identify the sources of performance differences between the two classes, namely, sensitivity to outliers and convergence instability of the quantizer scaling factor. Using those insights, we propose various techniques to improve the performance of both quantization methods - they fix the optimization instability issues present in the MSQE-based methods during quantization of MobileNet models and allow us to improve validation performance of the gradient-based methods by 4.0% and 3.3% for MobileNetV1 and MobileNetV2 on ImageNet respectively.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 30 references that are in the map. First posted on arXiv 7 Oct 2022.

Builds on

25 of 30 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  5. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  6. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  7. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  8. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  9. 2019Learned Step Size Quantizationcited by 628
  10. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 521
  11. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 467
  12. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 402
13 more
  1. 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 274
  2. 2019Limitations of the Empirical Fisher Approximation for Natural Gradient Descentcited by 217
  3. 2020LSQ+: Improving low-bit quantization through learnable offsets and better initializationcited by 189
  4. 2018Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Losscited by 160
  5. 2019Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networkscited by 148
  6. 2019Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networkscited by 90
  7. 2020Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectorscited by 80
  8. 2016Loss-aware Binarization of Deep Networkscited by 56
  9. 2016Towards the Limit of Network Quantizationcited by 50
  10. 2020PROFIT: A Novel Training Method for sub-4-bit MobileNet Modelscited by 50
  11. 2020HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNscited by 43
  12. 2018Loss-aware Weight Quantization of Deep Networkscited by 31
  13. 2019Deep Neural Network Approximation for Custom Hardware: Where We've Been, Where We're Goingcited by 13

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference
  2. 2025Low-bit Model Quantization for Deep Neural Networks: A Survey
  3. 2022A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification
  4. 2021Hardware-friendly Deep Learning by Network Quantization and Binarization
  5. 2025Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference
  6. 2021Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded Platforms
  7. 2022Power-of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networks
  8. 2021Confounding Tradeoffs for Neural Network Quantization