mlsanityData to 14 Oct 2026

Frame Quantization of Neural Networks

arXiv 2404.08131 ↗First posted 11 Apr 2024cs.LG cs.IT math.ITcited by 2

Not on the map. Why?

Abstract (arXiv)

We present a post-training quantization algorithm with error estimates relying on ideas originating from frame theory. Specifically, we use first-order Sigma-Delta (SigmaDelta) quantization for finite unit-norm tight frames to quantize weight matrices and biases in a neural network. In our scenario, we derive an error bound between the original neural network and the quantized neural network in terms of step size and the number of frame elements. We also demonstrate how to leverage the redundancy of frames to achieve a quantized neural network with higher accuracy.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 44 references that are in the map. First posted on arXiv 11 Apr 2024.

Builds on

18 of 44 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  4. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  5. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 621
  6. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  7. 2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 526
  8. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 180
  9. 2019Loss Aware Post-training Quantizationcited by 97
  10. 2022SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximationcited by 55
  11. 2022Post-training Quantization for Neural Networks with Provable Guaranteescited by 33
  12. 2018BinaryRelax: A Relaxation Approach For Training Deep Neural Networks With Quantized Weightscited by 24
6 more
  1. 2020A Greedy Algorithm for Quantizing Neural Networkscited by 22
  2. 2021Adaptive Precision Training (AdaPT): A dynamic fixed point quantized training approach for DNNscited by 8
  3. 2022A simple approach for quantizing neural networkscited by 8
  4. 2021Approximation of functions with one-bit neural networkscited by 5
  5. 2020Recurrence of Optimum for Training Weight and Activation Quantized Networkscited by 3
  6. 2021Sigma-Delta and Distributed Noise-Shaping Quantization Methods for Random Fourier Featurescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantizationcited by 28
  2. 2026Fine-Tuning of Transformer models with Framescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Neural Network Quantization by Learning Low-Loss Subspaces
  2. 2024QGen: On the Ability to Generalize in Quantization Aware Training
  3. 2023SPFQ: A Stochastic Algorithm and Its Error Analysis for Neural Network Quantization
  4. 2021Neural Network Quantization for Efficient Inference: A Survey
  5. 2022On Quantizing Implicit Neural Representations
  6. 2021Learnable Companding Quantization for Accurate Low-bit Neural Networks
  7. 2025Low-bit Model Quantization for Deep Neural Networks: A Survey
  8. 2024Gradient-Free Training of Quantized Neural Networks