Latent Weight Quantization for Integerized Training of Deep Neural Networks

Wen Fei;Wenrui Dai;Liang Zhang;Luoming Zhang;Chenglin Li;Junni Zou;Hongkai Xiong
{"title":"Latent Weight Quantization for Integerized Training of Deep Neural Networks","authors":"Wen Fei;Wenrui Dai;Liang Zhang;Luoming Zhang;Chenglin Li;Junni Zou;Hongkai Xiong","doi":"10.1109/TPAMI.2025.3527498","DOIUrl":null,"url":null,"abstract":"Existing methods for integerized training speed up deep learning by using low-bitwidth integerized weights, activations, gradients, and optimizer buffers. However, they overlook the issue of full-precision latent weights, which consume excessive memory to accumulate gradient-based updates for optimizing the integerized weights. In this paper, we propose the first latent weight quantization schema for general integerized training, which minimizes quantization perturbation to training process via residual quantization with optimized dual quantizer. We leverage residual quantization to eliminate the correlation between latent weight and integerized weight for suppressing quantization noise. We further propose dual quantizer with optimal nonuniform codebook to avoid frozen weight and ensure statistically unbiased training trajectory as full-precision latent weight. The codebook is optimized to minimize the disturbance on weight update under importance guidance and achieved with a three-segment polyline approximation for hardware-friendly implementation. Extensive experiments show that the proposed schema allows integerized training with lowest 4-bit latent weight for various architectures including ResNets, MobileNetV2, and Transformers, and yields negligible performance loss in image classification and text generation. Furthermore, we successfully fine-tune Large Language Models with up to 13 billion parameters on one single GPU using the proposed schema.","PeriodicalId":94034,"journal":{"name":"IEEE transactions on pattern analysis and machine intelligence","volume":"47 4","pages":"2816-2832"},"PeriodicalIF":0.0000,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on pattern analysis and machine intelligence","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10834560/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Existing methods for integerized training speed up deep learning by using low-bitwidth integerized weights, activations, gradients, and optimizer buffers. However, they overlook the issue of full-precision latent weights, which consume excessive memory to accumulate gradient-based updates for optimizing the integerized weights. In this paper, we propose the first latent weight quantization schema for general integerized training, which minimizes quantization perturbation to training process via residual quantization with optimized dual quantizer. We leverage residual quantization to eliminate the correlation between latent weight and integerized weight for suppressing quantization noise. We further propose dual quantizer with optimal nonuniform codebook to avoid frozen weight and ensure statistically unbiased training trajectory as full-precision latent weight. The codebook is optimized to minimize the disturbance on weight update under importance guidance and achieved with a three-segment polyline approximation for hardware-friendly implementation. Extensive experiments show that the proposed schema allows integerized training with lowest 4-bit latent weight for various architectures including ResNets, MobileNetV2, and Transformers, and yields negligible performance loss in image classification and text generation. Furthermore, we successfully fine-tune Large Language Models with up to 13 billion parameters on one single GPU using the proposed schema.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
深度神经网络综合训练的潜在权量化
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
2024 Reviewers List* Rate-Distortion Theory in Coding for Machines and its Applications. Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines. Class-Agnostic Repetitive Action Counting Using Wearable Devices. On the Upper Bounds of Number of Linear Regions and Generalization Error of Deep Convolutional Neural Networks.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1