Tensor Principal Component Analysis in High Dimensional CP Models

DOI10.1109/TIT.2022.3203972MaRDI QIDQ6193586zbMATH OpenFDO

Authors

Publication date 18 March 2024

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2108.04428

zbMATH Keywords

dimension reductionPCAunfoldingorthogonal projectionCP decompositionspiked covariancetensor principal component analysis

Mathematics Subject Classification ID

Information and communication theory, circuits (94-XX)

Abstract: The CP decomposition for high dimensional non-orthogonal spiked tensors is an important problem with broad applications across many disciplines. However, previous works with theoretical guarantee typically assume restrictive incoherence conditions on the basis vectors for the CP components. In this paper, we propose new computationally efficient composite PCA and concurrent orthogonalization algorithms for tensor CP decomposition with theoretical guarantees under mild incoherence conditions. The composite PCA applies the principal component or singular value decompositions twice, first to a matrix unfolding of the tensor data to obtain singular vectors and then to the matrix folding of the singular vectors obtained in the first step. It can be used as an initialization for any iterative optimization schemes for the tensor CP decomposition. The concurrent orthogonalization algorithm iteratively estimates the basis vector in each mode of the tensor by simultaneously applying projections to the orthogonal complements of the spaces generated by other CP components in other modes. It is designed to improve the alternating least squares estimator and other forms of the high order orthogonal iteration for tensors with low or moderately high CP ranks, and it is guaranteed to converge rapidly when the error of any given initial estimator is bounded by a small constant. Our theoretical investigation provides estimation accuracy and convergence rates for the two proposed algorithms. Both proposed algorithms are applicable to deterministic tensor, its noisy version, and the order-$2K$ covariance tensor of order-$K$ tensor data in a factor model with uncorrelated factors. Our implementations on synthetic data demonstrate significant practical superiority of our approach over existing methods.

Cited in

(5)

• Tensor robust principal component analysis via the tensor nuclear over Frobenius norm
• Deflated HeteroPCA: overcoming the curse of ill-conditioning in heteroskedastic PCA
• Tensor factor model estimation by iterative projection
• Tail-robust factor modelling of vector and tensor time series in high dimensions
• CP factor model for dynamic tensors

This page was built for publication: Tensor Principal Component Analysis in High Dimensional CP Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6193586)