Sparse Higher-Order Principal Components Analysis

Genevera Allen
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, PMLR 22:27-36, 2012.

Abstract

Traditional tensor decompositions such as the CANDECOMP / PARAFAC (CP) and Tucker decompositions yield higher-order principal components that have been used to understand tensor data in areas such as neuroimaging, microscopy, chemometrics, and remote sensing. Sparsity in high-dimensional matrix factorizations and principal components has been well-studied exhibiting many benefits; less attention has been given to sparsity in tensor decompositions. We propose two novel tensor decompositions that incorporate sparsity: the Sparse Higher-Order SVD and the Sparse CP Decomposition. The latter solves a 1-norm penalized relaxation of the single-factor CP optimization problem, thereby automatically selecting relevant features for each tensor factor. Through experiments and a scientific data analysis example, we demonstrate the utility of our methods for dimension reduction, feature selection, signal recovery, and exploratory data analysis of high-dimensional tensors.

Cite this Paper

BibTeX
@InProceedings{pmlr-v22-allen12, title = {Sparse Higher-Order Principal Components Analysis}, author = {Allen, Genevera}, booktitle = {Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics}, pages = {27--36}, year = {2012}, editor = {Lawrence, Neil D. and Girolami, Mark}, volume = {22}, series = {Proceedings of Machine Learning Research}, address = {La Palma, Canary Islands}, month = {21--23 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v22/allen12/allen12.pdf}, url = {https://proceedings.mlr.press/v22/allen12.html}, abstract = {Traditional tensor decompositions such as the CANDECOMP / PARAFAC (CP) and Tucker decompositions yield higher-order principal components that have been used to understand tensor data in areas such as neuroimaging, microscopy, chemometrics, and remote sensing. Sparsity in high-dimensional matrix factorizations and principal components has been well-studied exhibiting many benefits; less attention has been given to sparsity in tensor decompositions. We propose two novel tensor decompositions that incorporate sparsity: the Sparse Higher-Order SVD and the Sparse CP Decomposition. The latter solves a 1-norm penalized relaxation of the single-factor CP optimization problem, thereby automatically selecting relevant features for each tensor factor. Through experiments and a scientific data analysis example, we demonstrate the utility of our methods for dimension reduction, feature selection, signal recovery, and exploratory data analysis of high-dimensional tensors.} }
Endnote
%0 Conference Paper %T Sparse Higher-Order Principal Components Analysis %A Genevera Allen %B Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2012 %E Neil D. Lawrence %E Mark Girolami %F pmlr-v22-allen12 %I PMLR %P 27--36 %U https://proceedings.mlr.press/v22/allen12.html %V 22 %X Traditional tensor decompositions such as the CANDECOMP / PARAFAC (CP) and Tucker decompositions yield higher-order principal components that have been used to understand tensor data in areas such as neuroimaging, microscopy, chemometrics, and remote sensing. Sparsity in high-dimensional matrix factorizations and principal components has been well-studied exhibiting many benefits; less attention has been given to sparsity in tensor decompositions. We propose two novel tensor decompositions that incorporate sparsity: the Sparse Higher-Order SVD and the Sparse CP Decomposition. The latter solves a 1-norm penalized relaxation of the single-factor CP optimization problem, thereby automatically selecting relevant features for each tensor factor. Through experiments and a scientific data analysis example, we demonstrate the utility of our methods for dimension reduction, feature selection, signal recovery, and exploratory data analysis of high-dimensional tensors.
RIS
TY - CPAPER TI - Sparse Higher-Order Principal Components Analysis AU - Genevera Allen BT - Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics DA - 2012/03/21 ED - Neil D. Lawrence ED - Mark Girolami ID - pmlr-v22-allen12 PB - PMLR DP - Proceedings of Machine Learning Research VL - 22 SP - 27 EP - 36 L1 - http://proceedings.mlr.press/v22/allen12/allen12.pdf UR - https://proceedings.mlr.press/v22/allen12.html AB - Traditional tensor decompositions such as the CANDECOMP / PARAFAC (CP) and Tucker decompositions yield higher-order principal components that have been used to understand tensor data in areas such as neuroimaging, microscopy, chemometrics, and remote sensing. Sparsity in high-dimensional matrix factorizations and principal components has been well-studied exhibiting many benefits; less attention has been given to sparsity in tensor decompositions. We propose two novel tensor decompositions that incorporate sparsity: the Sparse Higher-Order SVD and the Sparse CP Decomposition. The latter solves a 1-norm penalized relaxation of the single-factor CP optimization problem, thereby automatically selecting relevant features for each tensor factor. Through experiments and a scientific data analysis example, we demonstrate the utility of our methods for dimension reduction, feature selection, signal recovery, and exploratory data analysis of high-dimensional tensors. ER -
APA
Allen, G.. (2012). Sparse Higher-Order Principal Components Analysis. Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 22:27-36 Available from https://proceedings.mlr.press/v22/allen12.html.

Related Material