.png){kind=icon}
返回
Deep Network Quantization via Error Compensation
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2021.3064293.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
For portable devices with limited resources, it is often difficult to deploy deep networks due to the prohibitive computational overhead. Numerous approaches have been proposed to quantize weights and/or activations to speed up the inference. Loss-aware quantization has been proposed to directly formulate the impact of weight quantization on the model's final loss. However, we discover that, under certain circumstances, such a method may not converge and end up oscillating. To tackle this issue, we introduce a novel loss-aware quantization algorithm to efficiently compress deep networks with low bit-width model weights. We provide a more accurate estimation of gradients by leveraging the Taylor expansion to compensate for the quantization error, which leads to better convergence behavior. Our theoretical analysis indicates that the gradient mismatch issue can be fixed by the newly introduced quantization error compensation term. Experimental results for both linear models and convolutional networks verify the effectiveness of our proposed method.
Keyword:
Quantization (signal)
Taylor series
Optimization
Neural networks
Training
Computational modeling
Approximation algorithms
Deep learning
network compression
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
.png){kind=icon}
A Hierarchical Cardiac Rhythm Classification Methodology Based on Electrocardiogram Fiducial Points一种基于心电图基准点的分层心律分类方法
OAAI
OAAI分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏
查看更多内容