ITP OpenIR  > 理论物理所科研产出  > SCI论文
Han, ZY; Wang, J; Fan, H1,3; Wang, L1,3; Zhang, P2
Unsupervised Generative Modeling Using Matrix Product States
发表期刊PHYSICAL REVIEW X
语种英语
关键词NEURAL-NETWORKS RENORMALIZATION-GROUP BOLTZMANN MACHINES TENSOR NETWORKS ALGORITHM SYSTEMS
摘要Generative modeling, which learns joint probability distribution from data and generates samples according to it, is an important task in machine learning and artificial intelligence. Inspired by probabilistic interpretation of quantum physics, we propose a generative model using matrix product states, which is a tensor network originally proposed for describing (particularly one-dimensional) entangled quantum states. Our model enjoys efficient learning analogous to the density matrix renormalization group method, which allows dynamically adjusting dimensions of the tensors and offers an efficient direct sampling approach for generative tasks. We apply our method to generative modeling of several standard data sets including the Bars and Stripes random binary patterns and the MNIST handwritten digits to illustrate the abilities, features, and drawbacks of our model over popular generative models such as the Hopfield model, Boltzmann machines, and generative adversarial networks. Our work sheds light on many interesting directions of future exploration in the development of quantum-inspired algorithms for unsupervised machine learning, which are promisingly possible to realize on quantum devices.
2018
ISSN2160-3308
卷号8期号:3页码:31012
学科领域Physics
学科门类Physics, Multidisciplinary
DOI10.1103/PhysRevX.8.031012
收录类别SCIE
引用统计
被引频次:7[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.itp.ac.cn/handle/311006/22862
专题理论物理所科研产出_SCI论文
作者单位1.Peking Univ, Sch Phys, Beijing 100871, Peoples R China
2.Chinese Acad Sci, Inst Phys, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Inst Theoret Phys, Key Lab Theoret Phys, Beijing 100190, Peoples R China
4.Univ Chinese Acad Sci, CAS Ctr Excellence Topol Quantum Computat, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Han, ZY,Wang, J,Fan, H,et al. Unsupervised Generative Modeling Using Matrix Product States[J]. PHYSICAL REVIEW X,2018,8(3):31012.
APA Han, ZY,Wang, J,Fan, H,Wang, L,&Zhang, P.(2018).Unsupervised Generative Modeling Using Matrix Product States.PHYSICAL REVIEW X,8(3),31012.
MLA Han, ZY,et al."Unsupervised Generative Modeling Using Matrix Product States".PHYSICAL REVIEW X 8.3(2018):31012.
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
[Han, ZY]的文章
[Wang, J]的文章
[Fan, H]的文章
百度学术
百度学术中相似的文章
[Han, ZY]的文章
[Wang, J]的文章
[Fan, H]的文章
必应学术
必应学术中相似的文章
[Han, ZY]的文章
[Wang, J]的文章
[Fan, H]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。