用精确的QUBO模型优化神经网络量化，提升压缩后精度。
Optimization of the quantization of dense neural networks from an exact QUBO formulation
- 基于ADAROUND构建权重/偏置四舍五入选择的精确QUBO模型。
- 在MNIST等数据集上，相比传统四舍五入方法，精度提升0.5%~3.2%。
- 适合对模型压缩后精度要求高的工程部署场景。
本文提出一种基于新型ADAROUND的精确QUBO公式化方法，用于密集神经网络的训练后量化（PTQ）。以理论输出与反量化输出（激活前）之间的Frobenius距离为优化目标，获得一个二值变量表示每个权重和偏置四舍五入选择的显式QUBO。通过利用系数QUBO矩阵的结构，全局问题可被精确分解为n个独立的大小为f+1的子问题，可使用模拟退火等启发式算法高效求解。该方法在MNIST、Fashion-MNIST、EMNIST和CIFAR-10上，针对int8至int1的整数精度进行了评估，并与传统的四舍五入量化方法进行比较。
原文摘要 · Abstract (English)
This work introduces a post-training quantization (PTQ) method for dense neural networks via a novel ADAROUND-based QUBO formulation. Using the Frobenius distance between the theoretical output and the dequantized output (before the activation function) as the objective, an explicit QUBO whose binary variables represent the rounding choice for each weight and bias is obtained. Additionally, by exploiting the structure of the coefficient QUBO matrix, the global problem can be exactly decomposed into $n$ independent subproblems of size $f+1$, which can be efficiently solved using some heuristics such as simulated annealing. The approach is evaluated on MNIST, Fashion-MNIST, EMNIST, and CIFAR-10 across integer precisions from int8 to int1 and compared with a round-to-nearest traditional quantization methodology.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。