Exact Low Tubal Rank Tensor Recovery from Gaussian Measurements

06/07/2018
by   Canyi Lu, et al.
2

The recent proposed Tensor Nuclear Norm (TNN) [Lu et al., 2016; 2018a] is an interesting convex penalty induced by the tensor SVD [Kilmer and Martin, 2011]. It plays a similar role as the matrix nuclear norm which is the convex surrogate of the matrix rank. Considering that the TNN based Tensor Robust PCA [Lu et al., 2018a] is an elegant extension of Robust PCA with a similar tight recovery bound, it is natural to solve other low rank tensor recovery problems extended from the matrix cases. However, the extensions and proofs are generally tedious. The general atomic norm provides a unified view of low-complexity structures induced norms, e.g., the ℓ_1-norm and nuclear norm. The sharp estimates of the required number of generic measurements for exact recovery based on the atomic norm are known in the literature. In this work, with a careful choice of the atomic set, we prove that TNN is a special atomic norm. Then by computing the Gaussian width of certain cone which is necessary for the sharp estimate, we achieve a simple bound for guaranteed low tubal rank tensor recovery from Gaussian measurements. Specifically, we show that by solving a TNN minimization problem, the underlying tensor of size n_1× n_2× n_3 with tubal rank r can be exactly recovered when the given number of Gaussian measurements is O(r(n_1+n_2-r)n_3). It is order optimal when comparing with the degrees of freedom r(n_1+n_2-r)n_3. Beyond the Gaussian mapping, we also give the recovery guarantee of tensor completion based on the uniform random mapping by TNN minimization. Numerical experiments verify our theoretical results.

READ FULL TEXT

page 7

page 9

page 10

page 12

page 13

research
04/10/2018

Tensor Robust Principal Component Analysis with A New Tensor Nuclear Norm

In this paper, we consider the Tensor Robust Principal Component Analysi...
research
06/05/2019

RIP-based performance guarantee for low-tubal-rank tensor recovery

The essential task of multi-dimensional data analysis focuses on the ten...
research
11/14/2017

Near-optimal sample complexity for convex tensor completion

We analyze low rank tensor completion (TC) using noisy measurements of a...
research
03/22/2015

Relaxed Leverage Sampling for Low-rank Matrix Completion

We consider the problem of exact recovery of any m× n matrix of rank ϱ f...
research
06/09/2023

Spectral gap-based deterministic tensor completion

Tensor completion is a core machine learning algorithm used in recommend...
research
04/23/2014

Forward - Backward Greedy Algorithms for Atomic Norm Regularization

In many signal processing applications, the aim is to reconstruct a sign...
research
09/06/2019

Recovery of Future Data via Convolution Nuclear Norm Minimization

This paper is about recovering the unseen future data from a given seque...

Please sign up or login with your details

Forgot password? Click here to reset