[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86560-en":3,"doc-seo-86560-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},86560,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Efficient Tuning Before Low-Bit Post-Training Quantization for Stochastic Gradient Descent-optimized Models","Post-training quantization (PTQ) reduces memory and enables efficient deployment, yet low-bit PTQ (2-bit/4-bit) can cause large accuracy drops. Existing approaches typically reconstruct quantization errors using an unconstrained full-precision (FP) model. This work argues that low-bit PTQ is limited both by error minimization and by the FP model’s quantization-error tolerance. It introduces Efficient Tuning Before Quantization (ETBQ), a pre-conditioning SGD-tuning stage using perturbations from weight/activation error distributions, improving robustness without fake-quantized QAT training.","Efficient Tuning Before Low-Bit Post-Training Quantization for Stochastic Gradient Descent-optimized Models  \nPeng Xia, Junbiao Pang*, Muhammad Ayub Sabir  \narXiv :2607 . 11359v1 [ cs .CV] 13 Jul 2026  \nAbstract—Post-training quantization (PTQ) compresses deep neural networks for deployment under limited memory and computational budgets. However, low-bit (i.e., 2-bit or 4-bit) PTQ often suffers from substantial performance degradation. Most existing PTQ methods operate on an unconstrained full-precision (FP) model and primarily address quantization errors through post-hoc reconstruction. We argue that low-bit PTQ accuracy is limited not only by post-quantization error minimization, but also by the quantization-error tolerance of a FP model itself. In this paper, we propose Efficient Tuning Before Quantization (ETBQ), a pre-conditioning tuning stage for Stochastic Gradient Descent (SGD)-optimized models before PTQ. During tuning, the FP model is optimized under perturbations sampled from the error distributions of weight and activation quantization, guiding the model toward a loss-landscape region that is less sensitive to the subsequent PTQ. Unlike QAT, ETBQ does not train a fake-quantized deployment model, which is computationally and memory intensive. Instead, ETBQ outputs a FP model that can be used by any PTQ backend. Experiments on CIFAR- 100, Tiny-ImageNet, ImageNet, and Cityscapes provide consistent evidence that ETBQ improves low-bit PTQ across diverse tasks. Under W2A4 settings, e.g., ETBQ improves over naive PTQ by 2.14% top-1 accuracy on Tiny-ImageNet and by 5.80% mIoU on Cityscapes. Code is available at [https://github.com/](https://github.com/)[ ](https://github.com/)xpxpxp2001xpxpxp/ETBQ.  \nIndex Terms—Post-training quantization, low-bit quantization, model compression, quantization robustness, loss landscape.  \nI. INTRODUCTION  \nTHE deployment of Deep Neural Networks (DNNs) on  \nedge devices has made model compression a critical challenge in efficient deep learning. Among compression techniques, model quantization [1], [2] is particularly attractive, as it reduces memory usage and enables low-precision integer computation. Post-Training Quantization (PTQ) [3]–[5] is an efficient paradigm that avoids full-dataset retraining required by Quantization-Aware Training (QAT) [6]–[8] . Despite its efficiency, PTQ suffers significant accuracy degradation at low-bit widths (i.e., 2-bit or 4-bit) when both weights and activations are quantized.  \nExisting PTQ methods mainly address accuracy degradation by mimicking the behavior of FP models. Representative approaches include learned weight rounding [3], block-wise output reconstruction [1], [9], stochastic activation perturbation [4], and prediction-difference-guided calibration [10] .  \n* Corresponding author(s) .  \nPeng Xia, Junbiao Pang, and M. Sabir are with the School of Information Science and Technology, Beijing University of Technology, Beijing 100124, China (e-mail: junbiao [pang@bjut.edu.cn](pang@bjut.edu.cn))  \nFig. 1. Comparison between Hessian spectral densities of ResNet-18 on CIFAR-100 . (a) Standard SGD model, with W2A4 accuracy of 76.47%(b) ETBQ-preconditioned model, with W2A4 quantization. ETBQ shifts the Hessian spectrum toward smaller eigenvalues, indicating a flatter loss basin and improved tolerance to low-bit quantization errors.  \nMore recent extensions sequentially reduce activation and weight errors [11] or recover quantization-induced information via lightweight compensation modules [12] . A fundamental question overlooked by conventional PTQ paradigms is: What intrinsic properties of FP models make them quantizationfriendly for low-bit PTQ? An intuitive yet largely underexplored hypothesis is that FP models must be robust to quantization-induced errors.  \nWe hypothesize that FP models residing in flatter loss basins are more likely to be quantization-friendly. To examine this hypothesis, we compare a standard SGD-optimized ResNet- 18 with its ET","cbCaicPqepuL0XKX","https://ap.wps.com/l/cbCaicPqepuL0XKX","pdf",1880712,3,1,12,"English","en",105,"# Introduction\n## Background: PTQ vs. QAT\n## Existing PTQ methods and their limitations\n## Proposed idea: quantization-friendly FP models\n# Method: ETBQ Framework\n## Pre-quantization tuning via error-distribution perturbations\n## Stabilization with stochastic weight averaging\n# Experiments and Results\n## Benchmarks across vision tasks\n## Gains under W2A4 settings\n# Contributions and Positioning","[{\"question\":\"What problem does PTQ face when moving to very low bit widths?\",\"answer\":\"Low-bit PTQ (e.g., 2-bit or 4-bit) often leads to substantial performance degradation compared with full-precision baselines.\"},{\"question\":\"How does ETBQ differ from Quantization-Aware Training (QAT)?\",\"answer\":\"ETBQ performs a pre-conditioning tuning stage on the full-precision model using sampled quantization-error perturbations, without training a fake-quantized deployment model like QAT.\"},{\"question\":\"What types of evidence show ETBQ improves low-bit PTQ accuracy?\",\"answer\":\"Experiments on CIFAR-100, Tiny-ImageNet, ImageNet, and Cityscapes consistently show improvements; for example, ETBQ improves over naive PTQ by 2.14% top-1 on Tiny-ImageNet and by 5.80% mIoU on Cityscapes under W2A4 settings.\"}]",1784212635,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"efficient-tuning-before-low-bit-post-training-quantization-for-stochastic-gradient-descent-optimized-models","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/efficient-tuning-before-low-bit-post-training-quantization-for-stochastic-gradient-descent-optimized-models/86560/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-28","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does PTQ face when moving to very low bit widths?","Question",{"text":75,"@type":76},"Low-bit PTQ (e.g., 2-bit or 4-bit) often leads to substantial performance degradation compared with full-precision baselines.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does ETBQ differ from Quantization-Aware Training (QAT)?",{"text":80,"@type":76},"ETBQ performs a pre-conditioning tuning stage on the full-precision model using sampled quantization-error perturbations, without training a fake-quantized deployment model like QAT.",{"name":82,"@type":73,"acceptedAnswer":83},"What types of evidence show ETBQ improves low-bit PTQ accuracy?",{"text":84,"@type":76},"Experiments on CIFAR-100, Tiny-ImageNet, ImageNet, and Cityscapes consistently show improvements; for example, ETBQ improves over naive PTQ by 2.14% top-1 on Tiny-ImageNet and by 5.80% mIoU on Cityscapes under W2A4 settings.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]