Recent breakthrough methods in machine learning make use of increasingly large deep neural networks. The gains in performance have come at the cost of a substantial increase in computation and storage, making real-time implementation on limited hardware a very challenging task. One popular approach to address this challenge is to perform low-bit precision computations via neural network quantization. However, aggressive quantization generally entails a severe penalty in terms of accuracy and usually requires the retraining of the network or resorts to higher bit precision quantization. In this paper, we formalize the linear quantization task as a Minimum Mean Squared Error (MMSE) problem for both weights and activations. This allows low-bit precision inference without the need for full network retraining. The main contributions of our approach is the optimization of the constrained MSE problem at each layer of the network, the hardware aware partitioning of the neural network parameters, and the use of multiple low precision quantized tensors for poorly approximated layers. The proposed approach allows for the first time a linear 4 bits integer precision (INT4) quantization for deployment of pretrained models on limited hardware resources.

本文提出了一种在有限硬件资源上实现预训练模型的4位整数（INT4）量化的优化方法，将线性量化任务形式化为最小均方误差（MMSE）问题，并对网络的每一层进行限制MSE问题的优化以及多个量化张量的硬件感知分区，除少量精度降低外，在多种网络架构上实现最先进的结果。

神经网络的低位量化以提高推理效率