Guaranteed Functional Tensor Singular Value Decomposition
Abstract
This paper introduces the functional tensor singular value decomposition (FTSVD), a novel dimension reduction framework for tensors with one functional mode and several tabular modes. The problem is motivated by high-order longitudinal data analysis. Our model assumes the observed data to be a random realization of an approximate CP low-rank functional tensor measured on a discrete time grid. Incorporating tensor algebra and the theory of Reproducing Kernel Hilbert Space (RKHS), we propose a novel RKHS-based constrained power iteration with spectral initialization. Our method can successfully estimate both singular vectors and functions of the low-rank structure in the observed data. With mild assumptions, we establish the non-asymptotic contractive error bounds for the proposed algorithm. The superiority of the proposed framework is demonstrated via extensive experiments on both simulated and real data.
Cite
@article{arxiv.2108.04201,
title = {Guaranteed Functional Tensor Singular Value Decomposition},
author = {Rungang Han and Pixu Shi and Anru R. Zhang},
journal= {arXiv preprint arXiv:2108.04201},
year = {2023}
}
Comments
Journal of the American Statistical Association, to appear