Quantization replaces floating point arithmetic with integer arithmetic in deep neural network models, providing more efficient on-device inference with less power and memory. In this work, we propose a framework for formally verifying properties of quantized neural networks. Our baseline technique is based on integer linear programming which guarantees both soundness and completeness. We then show how efficiency can be improved by utilizing gradient-based heuristic search methods and also bound-propagation techniques. We evaluate our approach on perception networks quantized with PyTorch. Our results show that we can verify quantized networks with better scalability and efficiency than the previous state of the art.
@article{arxiv.2312.12679,
title = {Towards Efficient Verification of Quantized Neural Networks},
author = {Pei Huang and Haoze Wu and Yuting Yang and Ieva Daukantas and Min Wu and Yedi Zhang and Clark Barrett},
journal= {arXiv preprint arXiv:2312.12679},
year = {2023}
}