中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 复杂系统认知与决策实验室
  5. 类脑芯片与系统研究
Bayesian Automatic Model Compression

文献类型：期刊论文

作者Wang, Jiaxing1,4; Bai, Haoli3; Wu, Jiaxiang2; Cheng, Jian1,5,6
刊名IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING
出版日期2020-05-01
卷号14期号:4页码:727-736
关键词Quantization (signal) Bayes methods Mathematical model Training Mixture models Optimization Machine learning Bayesian learning model compression automatic machine learning quantizartion explainability
ISSN号1932-4553
DOI10.1109/JSTSP.2020.2977090
通讯作者Cheng, Jian(jcheng@nlpr.ia.ac.cn)
英文摘要Model compression has drawn great attention in deep learning community. A core problem in model compression is to determine the layer-wise optimal compression policy, e.g., the layer-wise bit-width in network quantization. Conventional hand-crafted heuristics rely on human experts and are usually sub-optimal, while recent reinforcement learning based approaches can be inefficient during the exploration of the policy space. In this article, we propose Bayesian automatic model compression (BAMC), which leverages non-parametric Bayesian methods to learn the optimal quantization bit-width for each layer of the network. BAMC is trained in a one-shot manner, avoiding the back and forth (re)-training in reinforcement learning based approaches. Experimental results on various datasets validate that our proposed methods can find reasonable quantization policies efficiently with little accuracy drop for the quantized network.
资助项目National Natural Science Foundation of China[61876182] ; National Natural Science Foundation of China[61906193] ; National Natural Science Foundation of China[61906195] ; Strategic Priority Research Program of Chinese Academy of Science[XDB32050200] ; Advance Research Program[31511130301]
WOS研究方向Engineering
语种英语
WOS记录号WOS:000565858900011
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China ; Strategic Priority Research Program of Chinese Academy of Science ; Advance Research Program
源URL[http://ir.ia.ac.cn/handle/173211/41513]  
专题类脑芯片与系统研究
通讯作者Cheng, Jian
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Tencent AI Lab, Machine Learning Grp, Shenzhen 518000, Peoples R China
3.Chinese Univ Hong Kong, Dept Comp Sci & Engn, Hong Kong 999077, Peoples R China
4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
5.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China
6.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Jiaxing,Bai, Haoli,Wu, Jiaxiang,et al. Bayesian Automatic Model Compression[J]. IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING,2020,14(4):727-736.
APA Wang, Jiaxing,Bai, Haoli,Wu, Jiaxiang,&Cheng, Jian.(2020).Bayesian Automatic Model Compression.IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING,14(4),727-736.
MLA Wang, Jiaxing,et al."Bayesian Automatic Model Compression".IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING 14.4(2020):727-736.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。