Modewise Operators, the Tensor Restricted Isometry Property, and Low-Rank Tensor Recovery

by   Mark A. Iwen, et al.
Princeton University
Michigan State University

Recovery of sparse vectors and low-rank matrices from a small number of linear measurements is well-known to be possible under various model assumptions on the measurements. The key requirement on the measurement matrices is typically the restricted isometry property, that is, approximate orthonormality when acting on the subspace to be recovered. Among the most widely used random matrix measurement models are (a) independent sub-gaussian models and (b) randomized Fourier-based models, allowing for the efficient computation of the measurements. For the now ubiquitous tensor data, direct application of the known recovery algorithms to the vectorized or matricized tensor is awkward and memory-heavy because of the huge measurement matrices to be constructed and stored. In this paper, we propose modewise measurement schemes based on sub-gaussian and randomized Fourier measurements. These modewise operators act on the pairs or other small subsets of the tensor modes separately. They require significantly less memory than the measurements working on the vectorized tensor, provably satisfy the tensor restricted isometry property and experimentally can recover the tensor data from fewer measurements and do not require impractical storage.


page 1

page 2

page 3

page 4


Tensor Restricted Isometry Property Analysis For a Large Class of Random Measurement Ensembles

In previous work, theoretical analysis based on the tensor Restricted Is...

Optimal low rank tensor recovery

We investigate the sample size requirement for exact recovery of a high ...

Iterative Hard Thresholding for Low CP-rank Tensor Models

Recovery of low-rank matrices from a small number of linear measurements...

Generalized notions of sparsity and restricted isometry property. Part II: Applications

The restricted isometry property (RIP) is a universal tool for data reco...

Exact and Stable Covariance Estimation from Quadratic Sampling via Convex Programming

Statistical inference and information processing of high-dimensional dat...

Improved Lower Bounds for the Restricted Isometry Property of Subsampled Fourier Matrices

Let A be an N × N Fourier matrix over F_p^N/p for some prime p. We impro...

Guarantees of Augmented Trace Norm Models in Tensor Recovery

This paper studies the recovery guarantees of the models of minimizing X...

Please sign up or login with your details

Forgot password? Click here to reset