Incoherent Tensor Norms and Their Applications in Higher Order Tensor Completion

TL;DR

This paper introduces incoherent tensor norms for higher order tensor completion, showing that tensors can be recovered from fewer samples by leveraging incoherence, with theoretical guarantees on sample complexity.

Contribution

It proposes a new class of tensor norms that incorporate incoherence, providing improved sample complexity bounds for tensor completion.

Findings

Tensor completion is feasible with fewer samples using incoherent norms.

The sample complexity depends on tensor rank, dimension, and order.

Highlighting the importance of incoherence in higher order tensor recovery.

Abstract

In this paper, we investigate the sample size requirement for a general class of nuclear norm minimization methods for higher order tensor completion. We introduce a class of tensor norms by allowing for different levels of coherence, which allows us to leverage the incoherence of a tensor. In particular, we show that a $k$th order tensor of rank $r$ and dimension $d\times\cdots\times d$ can be recovered perfectly from as few as $O((r^{(k-1)/2}d^{3/2}+r^{k-1}d)(\log(d))^2)$ uniformly sampled entries through an appropriate incoherent nuclear norm minimization. Our results demonstrate some key differences between completing a matrix and a higher order tensor: They not only point to potential room for improvement over the usual nuclear norm minimization but also highlight the importance of explicitly accounting for incoherence, when dealing with higher order tensors.