Tensor Methods for Nonlinear Matrix Completion

In the low-rank matrix completion (LRMC) problem, the low-rank assumption means that the columns (or rows) of the matrix to be completed are points on a low-dimensional linear algebraic variety. This paper extends this thinking to cases where the columns are points on a low-dimensional nonlinear algebraic variety, a problem we call low algebraic dimension matrix completion (LADMC). Matrices whose columns belong to a union of subspaces are an important special case. We propose an LADMC algorithm that leverages existing LRMC methods on a tensorized representation of the data. For example, a second-order tensorized representation is formed by taking the Kronecker product of each column with itself, and we consider higher-order tensorizations as well. This approach will succeed in many cases where traditional LRMC is guaranteed to fail because the data are low-rank in the tensorized representation but are not in the original representation. We also provide a formal mathematical justification for the success of our method. In particular, we give bounds on the rank of these data in the tensorized representation, and we prove sampling requirements to guarantee uniqueness of the solution. We also provide experimental results showing that the new approach outperforms existing state-of-the-art methods for matrix completion under a union-of-subspaces model.

Automated summary

This study extends low-rank matrix completion to cases where columns are points on a low-dimensional nonlinear algebraic variety, proposing a low algebraic dimension matrix completion algorithm that leverages existing LRMC methods on tensorized data representations. Mathematical justification is provided for the success of the method, including rank bounds of data in tensorized representation and sampling requirements for solution uniqueness. Experimental results show the new approach outperforming existing methods for matrix completion under a union-of-subspaces model.