Cargando…

Learning from Binary Multiway Data: Probabilistic Tensor Decomposition and its Statistical Optimality

We consider the problem of decomposing a higher-order tensor with binary entries. Such data problems arise frequently in applications such as neuroimaging, recommendation system, topic modeling, and sensor network localization. We propose a multilinear Bernoulli model, develop a rank-constrained lik...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Miaoyan, Li, Lexin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8457422/
https://www.ncbi.nlm.nih.gov/pubmed/34557057
_version_ 1784571092493402112
author Wang, Miaoyan
Li, Lexin
author_facet Wang, Miaoyan
Li, Lexin
author_sort Wang, Miaoyan
collection PubMed
description We consider the problem of decomposing a higher-order tensor with binary entries. Such data problems arise frequently in applications such as neuroimaging, recommendation system, topic modeling, and sensor network localization. We propose a multilinear Bernoulli model, develop a rank-constrained likelihood-based estimation method, and obtain the theoretical accuracy guarantees. In contrast to continuous-valued problems, the binary tensor problem exhibits an interesting phase transition phenomenon according to the signal-to-noise ratio. The error bound for the parameter tensor estimation is established, and we show that the obtained rate is minimax optimal under the considered model. Furthermore, we develop an alternating optimization algorithm with convergence guarantees. The efficacy of our approach is demonstrated through both simulations and analyses of multiple data sets on the tasks of tensor completion and clustering.
format Online
Article
Text
id pubmed-8457422
institution National Center for Biotechnology Information
language English
publishDate 2020
record_format MEDLINE/PubMed
spelling pubmed-84574222021-09-22 Learning from Binary Multiway Data: Probabilistic Tensor Decomposition and its Statistical Optimality Wang, Miaoyan Li, Lexin J Mach Learn Res Article We consider the problem of decomposing a higher-order tensor with binary entries. Such data problems arise frequently in applications such as neuroimaging, recommendation system, topic modeling, and sensor network localization. We propose a multilinear Bernoulli model, develop a rank-constrained likelihood-based estimation method, and obtain the theoretical accuracy guarantees. In contrast to continuous-valued problems, the binary tensor problem exhibits an interesting phase transition phenomenon according to the signal-to-noise ratio. The error bound for the parameter tensor estimation is established, and we show that the obtained rate is minimax optimal under the considered model. Furthermore, we develop an alternating optimization algorithm with convergence guarantees. The efficacy of our approach is demonstrated through both simulations and analyses of multiple data sets on the tasks of tensor completion and clustering. 2020-07 /pmc/articles/PMC8457422/ /pubmed/34557057 Text en https://creativecommons.org/licenses/by/4.0/License: CC-BY 4.0, see https://creativecommons.org/licenses/by/4.0/. Attribution requirements are provided at http://jmlr.org/papers/v21/18-766.html.
spellingShingle Article
Wang, Miaoyan
Li, Lexin
Learning from Binary Multiway Data: Probabilistic Tensor Decomposition and its Statistical Optimality
title Learning from Binary Multiway Data: Probabilistic Tensor Decomposition and its Statistical Optimality
title_full Learning from Binary Multiway Data: Probabilistic Tensor Decomposition and its Statistical Optimality
title_fullStr Learning from Binary Multiway Data: Probabilistic Tensor Decomposition and its Statistical Optimality
title_full_unstemmed Learning from Binary Multiway Data: Probabilistic Tensor Decomposition and its Statistical Optimality
title_short Learning from Binary Multiway Data: Probabilistic Tensor Decomposition and its Statistical Optimality
title_sort learning from binary multiway data: probabilistic tensor decomposition and its statistical optimality
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8457422/
https://www.ncbi.nlm.nih.gov/pubmed/34557057
work_keys_str_mv AT wangmiaoyan learningfrombinarymultiwaydataprobabilistictensordecompositionanditsstatisticaloptimality
AT lilexin learningfrombinarymultiwaydataprobabilistictensordecompositionanditsstatisticaloptimality