Tensor Completion by Multi-Rank via Unitary Transformation

TL;DR

This paper proposes a tensor completion method using multi-rank and unitary transformations, providing bounds on sample entries needed for recovery and demonstrating effectiveness on synthetic and imaging data.

Contribution

It introduces a novel tensor completion bound based on multi-rank and unitary transformations, extending previous work beyond tubal rank.

Findings

Effective sample size bounds demonstrated on synthetic data

Method works with any unitary transformation in the T-SVD framework

Numerical experiments confirm theoretical predictions

Abstract

One of the key problems in tensor completion is the number of uniformly random sample entries required for recovery guarantee. The main aim of this paper is to study $n_1 \times n_2 \times n_3$ third-order tensor completion based on transformed tensor singular value decomposition, and provide a bound on the number of required sample entries. Our approach is to make use of the multi-rank of the underlying tensor instead of its tubal rank in the bound. In numerical experiments on synthetic and imaging data sets, we demonstrate the effectiveness of our proposed bound for the number of sample entries. Moreover, our theoretical results are valid to any unitary transformation applied to $n_3$-dimension under transformed tensor singular value decomposition.