CSpace  > 数学所
Clustering using matrix product states
Shi, Xiao1,2; Shang, Yun1,3; Guo, Chu1,4,5,6
2022-05-18
发表期刊PHYSICAL REVIEW A
ISSN2469-9926
卷号105期号:5页码:8
摘要The matrix product state has been demonstrated to be able to explore the most relevant portion of the exponentially large quantum Hilbert space and find accurate solutions for one-dimensional interacting quantum many-body systems. Inspired by this success, here we propose a clustering algorithm based on the matrix product state, which first maps the classical data into quantum states represented as matrix product states, and then minimizes the loss function using a variational matrix product states algorithm in the enlarged space. We demonstrate this algorithm by applying it to several commonly used machine learning data sets, showing that this algorithm could reach higher learning precision and that it is less likely to be trapped in local minima compared to the standard K-means algorithm. We also show that this algorithm can achieve state-of-the-art learning precision on popular computer vision data sets when used in combination with better initialization schemes.
DOI10.1103/PhysRevA.105.052424
收录类别SCI
语种英语
资助项目National Natural Science Foundation of China[11805279] ; National Natural Science Foundation of China[61833010] ; National Natural Science Foundation of China[12074117] ; National Natural Science Foundation of China[12061131011] ; Program for Creative Research Group of the National Natural Science Foundation of China[61621003]
WOS研究方向Optics ; Physics
WOS类目Optics ; Physics, Atomic, Molecular & Chemical
WOS记录号WOS:000804520400004
出版者AMER PHYSICAL SOC
引用统计
文献类型期刊论文
条目标识符http://ir.amss.ac.cn/handle/2S8OKBNM/61497
专题数学所
通讯作者Shang, Yun
作者单位1.Chinese Acad Sci, Acad Math & Syst Sci, Inst Math, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Math Sci, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Acad Math & Syst Sci, NCMIS, MDIS, Beijing 100190, Peoples R China
4.Henan Key Lab Quantum Informat & Cryptog, Zhengzhou 450000, Henan, Peoples R China
5.Hunan Normal Univ, Key Lab Low Dimens Quantum Struct & Quantum Contr, Minist Educ, Dept Phys, Changsha 410081, Peoples R China
6.Hunan Normal Univ, Synerget Innovat Ctr Quantum Effects & Applicat, Changsha 410081, Peoples R China
推荐引用方式
GB/T 7714
Shi, Xiao,Shang, Yun,Guo, Chu. Clustering using matrix product states[J]. PHYSICAL REVIEW A,2022,105(5):8.
APA Shi, Xiao,Shang, Yun,&Guo, Chu.(2022).Clustering using matrix product states.PHYSICAL REVIEW A,105(5),8.
MLA Shi, Xiao,et al."Clustering using matrix product states".PHYSICAL REVIEW A 105.5(2022):8.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Shi, Xiao]的文章
[Shang, Yun]的文章
[Guo, Chu]的文章
百度学术
百度学术中相似的文章
[Shi, Xiao]的文章
[Shang, Yun]的文章
[Guo, Chu]的文章
必应学术
必应学术中相似的文章
[Shi, Xiao]的文章
[Shang, Yun]的文章
[Guo, Chu]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。