# COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization Source: [COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization]() Collection index: [llms.txt]() Data updated: 2025-10-26T03:32:00.805Z Authors: Aozhong Zhang, Zi Yang, Naigang Wang, Yingyong Qi, Jack Xin, Xin Li, Penghang Yin Published: 2024-03-11T20:04:03.000Z ## Abstract Post-training quantization (PTQ) has emerged as a practical approach to compress large neural networks, making them highly efficient for deployment. However, effectively reducing these models to their low-bit counterparts without compromising the original accuracy remains a key challenge. In this paper, we propose an innovative PTQ algorithm termed COMQ, which sequentially conducts coordinate-wise minimization of the layer-wise reconstruction errors. We consider the widely used integer quantization, where every quantized weight can be decomposed into a shared floating-point scalar and an integer bit-code. Within a fixed layer, COMQ treats all the scaling factor(s) and bit-codes as the variables of the reconstruction error. Every iteration improves this error along a single coordinate while keeping all other variables constant. COMQ is easy to use and requires no hyper-parameter tuning. It instead involves only dot products and rounding operations. We update these variables in a carefully designed greedy order, significantly enhancing the accuracy. COMQ achieves remarkable results in quantizing 4-bit Vision Transformers, with a negligible loss of less than 1% in Top-1 accuracy. In 4-bit INT quantization of convolutional neural networks, COMQ maintains near-lossless accuracy with a minimal drop of merely 0.3% in Top-1 accuracy. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on ImageNet (val) (Accuracy Drop)](): Image Classification; ImageNet (val); Accuracy Drop: 0.59. - [Medical Image Segmentation on AbdomenCT-1K (test)](): Medical Image Segmentation; AbdomenCT-1K (test); DSC: 93.486. ## Original sources and implementation [Original paper]() [PDF]()