mlsanityData to 7 Oct 2026

Value-aware Quantization for Training and Inference of Neural Networks

arXiv 1804.07802 ↗First posted 20 Apr 2018cs.NE cs.LGcited by 49

Not on the map. Why?

Abstract (arXiv)

We propose a novel value-aware quantization which applies aggressively reduced precision to the majority of data while separately handling a small amount of large data in high precision, which reduces total quantization errors under very low precision. We present new techniques to apply the proposed quantization to training and inference. The experiments show that our method with 3-bit activations (with 2% of large ones) can give the same training accuracy as full-precision one while offering significant (41.6% and 53.7%) reductions in the memory cost of activations in ResNet-152 and Inception-v3 compared with the state-of-the-art method. Our experiments also show that deep networks such as Inception-v3, ResNet-101 and DenseNet-121 can be quantized for inference with 4-bit weights and activations (with 1% 16-bit data) within 1% top-1 accuracy drop.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 9; 2023: 9; 2024: 7; 2025: 4; 2026: 1.

49 papers.

Sort:

  1. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  2. 2021I-BERT: Integer-only BERT Quantizationcited by 250
  3. 2024BiLLM: Pushing the Limit of Post-Training Quantization for LLMscited by 137
  4. 2023OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Modelscited by 113
  5. 2022PD-Quant: Post-Training Quantization based on Prediction Difference Metriccited by 73
  6. 2021Diversifying Sample Generation for Accurate Data-Free Quantizationcited by 63
  7. 2021BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantizationcited by 37
  8. 2021OMPQ: Orthogonal Mixed Precision Quantizationcited by 37
  9. 2021DKM: Differentiable K-Means Clustering Layer for Neural Network Compressioncited by 31
  10. 2022F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantizationcited by 26
  11. 2023EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantizationcited by 22
  12. 2021Distance-aware Quantizationcited by 19
37 more
  1. 2021Post-Training Sparsity-Aware Quantizationcited by 16
  2. 2024SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compressioncited by 12
  3. 2021LANA: Latency Aware Network Accelerationcited by 11
  4. 2021Diverse Sample Generation: Pushing the Limit of Generative Data-free Quantizationcited by 11
  5. 2025Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunitiescited by 11
  6. 2021HPTQ: Hardware-Friendly Post Training Quantizationcited by 9
  7. 2024HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAscited by 9
  8. 2021Lightweight Compression of Intermediate Neural Network Features for Collaborative Intelligencecited by 7
  9. 2022Mixed-Precision Neural Networks: A Surveycited by 7
  10. 2024ViT-1.58b: Mobile Vision Transformers in the 1-bit Eracited by 7
  11. 2021Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Acceleratorscited by 6
  12. 2021RMSMP: A Novel Deep Neural Network Quantization Framework with Row-wise Mixed Schemes and Multiple Precisionscited by 6
  13. 2021A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statisticscited by 6
  14. 2022Machine Learning Sensorscited by 5
  15. 2022Analysis of Quantization on MLP-based Vision Modelscited by 5
  16. 2021Quantization of Generative Adversarial Networks for Efficient Inference: a Methodological Studycited by 4
  17. 2022Vertical Layering of Quantized Neural Networks for Heterogeneous Inferencecited by 4
  18. 2023eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Modelscited by 4
  19. 2021Rethinking Floating Point Overheads for Mixed Precision DNN Acceleratorscited by 3
  20. 2022Arrhythmia Classifier Using Convolutional Neural Network with Adaptive Loss-aware Multi-bit Networks Quantizationcited by 3
  21. 2022Symmetry Regularization and Saturating Nonlinearity for Robust Quantizationcited by 3
  22. 2023Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inferencecited by 3
  23. 2024Data-free Weight Compress and Denoise for Large Language Modelscited by 3
  24. 2021S2Engine: A Novel Systolic Architecture for Sparse Convolutional Neural Networkscited by 2
  25. 2025Energy-Efficient and Dequantization-Free Q-LLMs: A Spiking Neural Network Approach to Salient Value Mitigationcited by 2
  26. 2025DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Schedulingcited by 1
  27. 2021Compact representations of convolutional neural networks via weight pruning and quantizationcited by 0
  28. 2022CSMPQ:Class Separability Based Mixed-Precision Quantizationcited by 0
  29. 2023Remote Sensing Object Counting with Online Knowledge Learningcited by 0
  30. 2023Guaranteed Quantization Error Computation for Neural Network Model Compressioncited by 0
  31. 2023Designing strong baselines for ternary neural network quantization through support and mass equalizationcited by 0
  32. 2023Quantized Non-Volatile Nanomagnetic Synapse based Autoencoder for Efficient Unsupervised Network Anomaly Detectioncited by 0
  33. 2023QWID: Quantized Weed Identification Deep neural networkcited by 0
  34. 2024Diagnosing Robotics Systems Issues with Large Language Modelscited by 0
  35. 2024Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural Networkscited by 0
  36. 2025A Quantized VAE-MLP Botnet Detection Model: A Systematic Evaluation of Quantization-Aware Training and Post-Training Quantization Strategiescited by 0
  37. 2026Quantization in Federated Learning: Methods, Challenges and Future Directionscited by 0