Nonnegative Tensor Completion via Integer Optimization

Caleb Xavier Bugg, Chen Chen, Anil Aswani

Keywords: tensor completion, machine learning

Abstract: Unlike matrix completion, tensor completion does not have an algorithm that is known to achieve the information-theoretic sample complexity rate. This paper develops a new algorithm for the special case of completion for nonnegative tensors. We prove that our algorithm converges in a linear (in numerical tolerance) number of oracle steps, while achieving the information-theoretic rate. Our approach is to define a new norm for nonnegative tensors using the gauge of a particular 0-1 polytope; integer linear programming can, in turn, be used to solve linear separation problems over this polytope. We combine this insight with a variant of the Frank-Wolfe algorithm to construct our numerical algorithm, and we demonstrate its effectiveness and scalability through computational experiments using a laptop on tensors with up to one-hundred million entries.

TL;DR: We present a new norm for nonnegative tensor completion and demonstrate its usefulness, versus existing methods, through numerical experiments

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2111.04580/code)