Binary Random Projections with Controllable Sparsity Patterns  

作　　者：Wen-Ye Li Shu-Zhong Zhang 

机构地区：[1]The Chinese University of Hong Kong,Shenzhen 518172,Guangdong,China [2]Shenzhen Research Institute of Big Data,Shenzhen 518052,Guangdong,China [3]University of Minnesota,Minneapolis,MN 55455,USA

出　　处：《Journal of the Operations Research Society of China》2022年第3期507-528,共22页中国运筹学会会刊（英文）

基　　金：partially supported by Guangdong Fundamental Research Fund(No.2021A1515011825);Shenzhen Fundamental Research Fund(No.KQJSCX20170728162302784).

摘　　要：Random projection is often used to project higher-dimensional vectors onto a lower-dimensional space,while approximately preserving their pairwise distances.It has emerged as a powerful tool in various data processing tasks and has attracted considerable research interest.Partly motivated by the recent discoveries in neuroscience,in this paper we study the problem of random projection using binary matrices with controllable sparsity patterns.Specifically,we proposed two sparse binary projection models that work on general data vectors.Compared with the conventional random projection models with dense projection matrices,our proposed models enjoy significant computational advantages due to their sparsity structure,as well as improved accuracies in empirical evaluations.

关 键 词：Binary random projection SPARSITY Dimensionality 

分 类 号：O15[理学—数学]