English

Matrix Completion from Noisy Entries

Machine Learning 2012-04-10 v2 Machine Learning

Abstract

Given a matrix M of low-rank, we consider the problem of reconstructing it from noisy observations of a small, random subset of its entries. The problem arises in a variety of applications, from collaborative filtering (the `Netflix problem') to structure-from-motion and positioning. We study a low complexity algorithm introduced by Keshavan et al.(2009), based on a combination of spectral techniques and manifold optimization, that we call here OptSpace. We prove performance guarantees that are order-optimal in a number of circumstances.

Keywords

Cite

@article{arxiv.0906.2027,
  title  = {Matrix Completion from Noisy Entries},
  author = {Raghunandan H. Keshavan and Andrea Montanari and Sewoong Oh},
  journal= {arXiv preprint arXiv:0906.2027},
  year   = {2012}
}

Comments

22 pages, 3 figures

R2 v1 2026-06-21T13:12:10.544Z