A Novel Computational Model Enabling Continuous Differentiability in Neural Network Quantization

Yang, Yu

doi:10.3390/app16115281

A Novel Computational Model Enabling Continuous Differentiability in Neural Network Quantization

2026-05-01

0

PRE

AI

DOI：10.3390/app16115281

Original

Original request for help

Save

Abstract

En 中文

Quantization reduces the precision of neural network parameters to accelerate inference and lower power consumption, but it often causes noticeable accuracy degradation. We propose a differentiable quantization framework that replaces the non-differentiable rounding operation with a continuous surrogate function. During QAT, gradients are backpropagated through the proposed surrogate rather than being estimated by the STE, enabling gradient-based optimization of model weights, quantization parameters, and layer-wise bit-width configurations. Experiments on CIFAR-10 show that our method achieves higher accuracy than several representative quantization approximation methods under different bit-width settings. On embedded platforms, it improves post-quantization accuracy by up to 3.66 percentage points over industrial quantization frameworks such as TensorRT and Huawei AMCT on detection and segmentation tasks, and outperforms representative bit-width allocation methods by up to 7.49 percentage points. These results demonstrate the effectiveness of the proposed method for improving the accuracy of quantized neural networks on resource-constrained devices.

Keywords:

non-differentiability

rounding operation

gradient estimation

bit-width allocation

sensitivity

A Novel Computational Model Enabling Continuous Differentiability in Neural Network Quantization

Abstract

Journal

Organization

Cited Papers