mlsanityData to 14 Oct 2026

CEG4N: Counter-Example Guided Neural Network Quantization Refinement

arXiv 2207.04231 ↗First posted 9 Jul 2022cs.LG cs.AI cs.SEcited by 2

Not on the map. Why?

Abstract (arXiv)

Neural networks are essential components of learning-based software systems. However, their high compute, memory, and power requirements make using them in low resources domains challenging. For this reason, neural networks are often quantized before deployment. Existing quantization techniques tend to degrade the network accuracy. We propose Counter-Example Guided Neural Network Quantization Refinement (CEG4N). This technique combines search-based quantization and equivalence verification: the former minimizes the computational requirements, while the latter guarantees that the network's output does not change after quantization. We evaluate CEG4N~on a diverse set of benchmarks, including large and small networks. Our technique successfully quantizes the networks in our evaluation while producing models with up to 72% better accuracy than state-of-the-art techniques.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 17 of its 32 references that are in the map. First posted on arXiv 9 Jul 2022.

Builds on

17 of 32 references.

References · 17

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  3. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  4. 2016End to End Learning for Self-Driving Carscited by 1,009
  5. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  6. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 521
  7. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 426
  8. 2017A Survey of Model Compression and Acceleration for Deep Neural Networkscited by 301
  9. 2019Algorithms for Verifying Deep Neural Networkscited by 221
  10. 2017Verifying Properties of Binarized Deep Neural Networkscited by 79
  11. 2021The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Resultscited by 71
  12. 2021Introduction to Neural Network Verificationcited by 63
5 more
  1. 2022Post-training Quantization for Neural Networks with Provable Guaranteescited by 33
  2. 2022On Neural Network Equivalence Checking using SMT Solverscited by 10
  3. 2018A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretabilitycited by 8
  4. 2021Geometric Path Enumeration for Equivalence Verification of Neural Networkscited by 6
  5. 2016Sound and Automated Synthesis of Digital Stabilizing Controllers for Continuous Plantscited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 1.

2 papers.

  1. 2023NeuroCodeBench: a plain C neural network benchmark for software verificationcited by 3
  2. 2025Floating-Point Neural Network Verification at the Software Levelcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2023RepQ: Generalizing Quantization-Aware Training for Re-Parametrized Architectures
  2. 2021Confounding Tradeoffs for Neural Network Quantization
  3. 2021Pareto-Optimal Quantized ResNet Is Mostly 4-bit
  4. 2021A White Paper on Neural Network Quantization
  5. 2021Neural Network Quantization for Efficient Inference: A Survey
  6. 2026QuantForge: Discovering Residual Decompositions for MXFP4 Post-Training Quantization
  7. 2021Automated Backend-Aware Post-Training Quantization
  8. 2024Toward INT4 Fixed-Point Training via Exploring Quantization Error for Gradients