Matrix completion under interval uncertainty

Jakub Mareček*, Peter Richtárik, Martin Takáč

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

9 Scopus citations

Abstract

Matrix completion under interval uncertainty can be cast as a matrix completion problem with element-wise box constraints. We present an efficient alternating-direction parallel coordinate-descent method for the problem. We show that the method outperforms any other known method on a benchmark in image in-painting in terms of signal-to-noise ratio, and that it provides high-quality solutions for an instance of collaborative filtering with 100,198,805 recommendations within 5 minutes on a single personal computer.

Original languageEnglish (US)
Pages (from-to)35-43
Number of pages9
JournalEuropean Journal of Operational Research
Volume256
Issue number1
DOIs
StatePublished - Jan 1 2017

Bibliographical note

Funding Information:
The authors are grateful for the numerous suggestions of the anonymous reviewers as well as the editor that have helped them to improve both the presentation and contents of the paper. In addition, the first author acknowledges funding from the European Union Horizon 2020 Programme (Horizon2020/2014-2020), under grant agreement number 688380 . The second author would like to acknowledge support from the EPSRC Grant EP/K02325X/1 , Accelerated Coordinate Descent Methods for Big Data Optimization.

Publisher Copyright:
© 2016 The Authors

Keywords

  • Collaborative filtering
  • Coordinate descent
  • Large-scale optimization
  • Matrix completion
  • Robust optimization

ASJC Scopus subject areas

  • Computer Science(all)
  • Modeling and Simulation
  • Management Science and Operations Research
  • Information Systems and Management
  • Industrial and Manufacturing Engineering

Fingerprint

Dive into the research topics of 'Matrix completion under interval uncertainty'. Together they form a unique fingerprint.

Cite this