English

Information Theory of Matrix Completion

Information Theory 2014-02-19 v1 math.IT

Abstract

Matrix completion is a fundamental problem that comes up in a variety of applications like the Netflix problem, collaborative filtering, computer vision, and crowdsourcing. The goal of the problem is to recover a k-by-n unknown matrix from a subset of its noiseless (or noisy) entries. We define an information-theoretic notion of completion capacity C that quantifies the maximum number of entries that one observation of an entry can resolve. This number provides the minimum number m of entries required for reliable reconstruction: m=kn/C. Translating the problem into a distributed joint source-channel coding problem with encoder restriction, we characterize the completion capacity for a wide class of stochastic models of the unknown matrix and the observation process. Our achievability proof is inspired by that of the Slepian-Wolf theorem. For an arbitrary stochastic matrix, we derive an upper bound on the completion capacity.

Keywords

Cite

@article{arxiv.1402.4225,
  title  = {Information Theory of Matrix Completion},
  author = {Changho Suh},
  journal= {arXiv preprint arXiv:1402.4225},
  year   = {2014}
}

Comments

5 pages, submitted to the International Symposium on Information Theory 2014

R2 v1 2026-06-22T03:10:16.820Z