Low-Rank Approximation and Completion of Positive Tensors

TL;DR

This paper introduces a polynomial-time convex optimization approach for low-rank approximation and completion of positive tensors, overcoming NP-hardness and ill-posedness in the tensor case, with applications to statistical regression and biological data.

Contribution

It develops a convex reformulation for positive tensor decomposition, enabling efficient algorithms for low-rank approximation and completion, including rank-1 approximation and sparse tensor recovery.

Findings

Polynomial-time algorithms for positive tensor low-rank approximation.

Efficient tensor completion with polynomial measurements.

Improved performance in biological data analysis.

Abstract

Unlike the matrix case, computing low-rank approximations of tensors is NP-hard and numerically ill-posed in general. Even the best rank-1 approximation of a tensor is NP-hard. In this paper, we use convex optimization to develop polynomial-time algorithms for low-rank approximation and completion of positive tensors. Our approach is to use algebraic topology to define a new (numerically well-posed) decomposition for positive tensors, which we show is equivalent to the standard tensor decomposition in important cases. Though computing this decomposition is a nonconvex optimization problem, we prove it can be exactly reformulated as a convex optimization problem. This allows us to construct polynomial-time randomized algorithms for computing this decomposition and for solving low-rank tensor approximation problems. Among the consequences is that best rank-1 approximations of positive tensors can be computed in polynomial time. Our framework is next extended to the tensor completion problem, where noisy entries of a tensor are observed and then used to estimate missing entries. We provide a polynomial-time algorithm that for specific cases requires a polynomial (in tensor order) number of measurements, in contrast to existing approaches that require an exponential number of measurements. These algorithms are extended to exploit sparsity in the tensor to reduce the number of measurements needed. We conclude by providing a novel interpretation of statistical regression problems with categorical variables as tensor completion problems, and numerical examples with synthetic data and data from a bioengineered metabolic network show the improved performance of our approach on this problem.