Show simple item record

dc.contributor.authorPang, Jianye
dc.contributor.authorYi, Kai
dc.contributor.authorYin, Wanguang
dc.contributor.authorXu, Min
dc.date.accessioned2020-08-19T11:06:11Z
dc.date.available2020-08-19T11:06:11Z
dc.date.issued2020-08-12
dc.identifier.urihttp://hdl.handle.net/10754/664669
dc.description.abstractIn this technical report, we analyze Legendre decomposition for non-negative tensor in theory and application. In theory, the properties of dual parameters and dually flat manifold in Legendre decomposition are reviewed, and the process of tensor projection and parameter updating is analyzed. In application, a series of verification experiments and clustering experiments with parameters in submanifolds are carried out, hoping to find an effective lower dimensional representation of the input tensor. The experimental results show that the parameters in submanifolds have no ability to be directly represented as low-rank representations. Combined with analysis, we connect Legendre decomposition with neural networks and low-rank representation, and put forward some promising prospects.
dc.description.sponsorshipThis work was supported in part by U.S. National Institutes of Health (NIH) grant P41GM103712 and R01GM134020, U.S. National Science Foundation (NSF) grant DBI-1949629 and IIS-2007595.
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/2008.05095
dc.rightsArchived with thanks to arXiv
dc.titleExperimental Analysis of Legendre Decomposition in Machine Learning
dc.typePreprint
dc.contributor.departmentDepartment of Computer Science King Abdullah University of Science and Technology.
dc.eprint.versionPre-print
dc.contributor.institutionDepartment of Computer Science Xi’an Jiaotong University.
dc.contributor.institutionDepartment of Computer Science Southern University of Science and Technology.
dc.contributor.institutionComputational Biology Department Carnegie Mellon University.
dc.identifier.arxivid2008.05095
kaust.personYi, Kai
refterms.dateFOA2020-08-19T11:06:50Z


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
669.2Kb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record