Skip to main content

Learning Mixtures of Low-Rank Models

Author(s): Chen, Yanxi; Ma, Cong; Poor, H Vincent; Chen, Yuxin

To refer to this page use:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorChen, Yanxi-
dc.contributor.authorMa, Cong-
dc.contributor.authorPoor, H Vincent-
dc.contributor.authorChen, Yuxin-
dc.identifier.citationChen, Yanxi, Ma, Cong, Poor, H Vincent, Chen, Yuxin. (2021). Learning Mixtures of Low-Rank Models. IEEE Transactions on Information Theory, 67 (7), 4613 - 4636. doi:10.1109/tit.2021.3065700en_US
dc.description.abstractWe study the problem of learning mixtures of low-rank models, i.e. reconstructing multiple low-rank matrices from unlabelled linear measurements of each. This problem enriches two widely studied settings - low-rank matrix sensing and mixed linear regression - by bringing latent variables (i.e. unknown labels) and structural priors (i.e. low-rank structures) into consideration. To cope with the non-convexity issues arising from unlabelled heterogeneous data and low-complexity structure, we develop a three-stage meta-algorithm that is guaranteed to recover the unknown matrices with near-optimal sample and computational complexities under Gaussian designs. In addition, the proposed algorithm is provably stable against random noise. We complement the theoretical studies with empirical evidence that confirms the efficacy of our algorithm.en_US
dc.format.extent4613 - 4636en_US
dc.relation.ispartofIEEE Transactions on Information Theoryen_US
dc.rightsFinal published version. This is an open access article.en_US
dc.titleLearning Mixtures of Low-Rank Modelsen_US
dc.typeJournal Articleen_US

Files in This Item:
File Description SizeFormat 
Learning_Mixtures_of_Low-Rank_Models.pdf691.83 kBAdobe PDFView/Download

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.