RIP-based performance guarantee for low-tubal-rank tensor recovery
This provides the first theoretical performance guarantee for low-tubal-rank tensor recovery, addressing a gap in the literature for tensor compressed sensing.
The paper introduces a tensor Restricted Isometry Property (t-RIP) for the t-SVD framework and proves that low-tubal-rank tensors can be stably recovered from few linear noise measurements under certain t-RIP conditions via a Regularized Tensor Nuclear Norm Minimization model.
The essential task of tensor data analysis focuses on the tensor decomposition and the corresponding notion of rank. In this paper, by introducing the notion of tensor Singular Value Decomposition (t-SVD), we establish a Regularized Tensor Nuclear Norm Minimization (RTNNM) model for low-tubal-rank tensor recovery. As we know that many variants of the Restricted Isometry Property (RIP) have proven to be crucial analysis tools for sparse recovery. In the t-SVD framework, we initiatively define a novel tensor Restricted Isometry Property (t-RIP). Furthermore, we show that any third-order tensor $\boldsymbol{\mathcal{X}}$ can stably be recovered from few linear noise measurements under some certain t-RIP conditions via the RTNNM model. We note that, as far as the authors are aware, such kind of result has not previously been reported in the literature.