A non-backtracking method for long matrix and tensor completion

We consider the problem of low-rank rectangular matrix completion in the regime where the matrix of size is ``long", i.e., the aspect ratio diverges to infinity. Such matrices are of particular interest in the study of tensor completion, where they arise from the unfolding of a low-rank tensor. In the case where the sampling probability is , we propose a new spectral algorithm for recovering the singular values and left singular vectors of the original matrix based on a variant of the standard non-backtracking operator of a suitably defined bipartite weighted random graph, which we call a \textit{non-backtracking wedge operator}. When is above a Kesten-Stigum-type sampling threshold, our algorithm recovers a correlated version of the singular value decomposition of with quantifiable error bounds. This is the first result in the regime of bounded for weak recovery and the first for weak consistency when arbitrarily slowly without any polylog factors. As an application, for low-CP-rank orthogonal -tensor completion, we efficiently achieve weak recovery with sample size and weak consistency with sample size . A similar result is obtained for low-multilinear-rank tensor completion with many samples.
View on arXiv