mlsanityData to 14 Oct 2026

Quantization in Layer's Input is Matter

arXiv 2202.05137 ↗First posted 10 Feb 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we will show that the quantization in layer's input is more important than parameters' quantization for loss function. And the algorithm which is based on the layer's input quantization error is better than hessian-based mixed precision layout algorithm.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 22 references that are in the map. First posted on arXiv 10 Feb 2022.

Builds on

17 of 22 references.

References · 17

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  3. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  4. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  5. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  6. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 443
  7. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 402
  8. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
  9. 2019HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networkscited by 261
  10. 2018Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Searchcited by 125
  11. 2017Soft Weight-Sharing for Neural Network Compressioncited by 99
  12. 2019Loss Aware Post-training Quantizationcited by 97
5 more
  1. 2020HAWQV3: Dyadic Neural Network Quantizationcited by 60
  2. 2017Exploring the Regularity of Sparse Structure in Convolutional Neural Networkscited by 37
  3. 2020Search What You Want: Barrier Panelty NAS for Mixed Precision Quantizationcited by 32
  4. 2020Channel-wise Hessian Aware trace-Weighted Quantization of Neural Networkscited by 6
  5. 2019Relay: A High-Level Compiler for Deep Learningcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Saturation Makes Quantization Error Additive: A Coverage Model with a Certificate
  2. 2022AMED: Automatic Mixed-Precision Quantization for Edge Devices
  3. 2026Predicting Quantization Price for Selecting PTQ Configurations Before Deployment
  4. 2021Data-free mixed-precision quantization using novel sensitivity metric
  5. 2023A Practical Mixed Precision Algorithm for Post-Training Quantization
  6. 2022Mixed-Precision Inference Quantization: Radically Towards Faster inference speed, Lower Storage requirement, and Lower Loss
  7. 2026Layerwise Error Attribution for Fast and Robust Mixed-Precision Post-Training Quantization
  8. 2024Adaptive quantization with mixed-precision based on low-cost proxy