Sensing tensors with Gaussian filters

TL;DR

This paper extends compressed sensing techniques to low-rank tensor recovery, demonstrating that recent error bound methods effectively apply to tensors using nuclear norm and related penalizations.

Contribution

It adapts and applies recent Gaussian measurement error bounds to the tensor setting with nuclear norm and Romera-Paredes--Pontil penalizations.

Findings

Provides error bounds for tensor recovery

Uses nuclear norm and Romera-Paredes--Pontil penalization

Extends compressed sensing theory to tensors

Abstract

Sparse recovery from linear Gaussian measurements has been the subject of much investigation since the breaktrough papers \cite{CRT:IEEEIT06} and \cite{donoho2006compressed} on Compressed Sensing. Application to sparse vectors and sparse matrices via least squares penalized with sparsity promoting norms is now well understood using tools such as Gaussian mean width, statistical dimension and the notion of descent cones \cite{tropp2014convex} \cite{Vershynin:ArXivEstimation14}. Extention of these ideas to low rank tensor recovery is starting to enjoy considerable interest due to its many potential applications to Independent Component Analysis, Hidden Markov Models and Gaussian Mixture Models \cite{AnandkumarEtAl:JMLR14}, hyperspectral image analysis \cite{zhang2008tensor}, to name a few. In this paper, we demonstrate that the recent approach of \cite{Vershynin:ArXivEstimation14} provides very useful error bounds in the tensor setting using the nuclear norm or the Romera-Paredes--Pontil \cite{RomeraParedesPontil:NIPS13} penalization.