Matrix Completion from Noisy Entries

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, Montanari, and Oh (2010), 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.

Cite

Text

Keshavan et al. "Matrix Completion from  Noisy Entries." Journal of Machine Learning Research, 2010.

Markdown

[Keshavan et al. "Matrix Completion from  Noisy Entries." Journal of Machine Learning Research, 2010.](https://mlanthology.org/jmlr/2010/keshavan2010jmlr-matrix/)

BibTeX

@article{keshavan2010jmlr-matrix,
  title     = {{Matrix Completion from  Noisy Entries}},
  author    = {Keshavan, Raghunandan H. and Montanari, Andrea and Oh, Sewoong},
  journal   = {Journal of Machine Learning Research},
  year      = {2010},
  pages     = {2057-2078},
  volume    = {11},
  url       = {https://mlanthology.org/jmlr/2010/keshavan2010jmlr-matrix/}
}