An experimental study of balance in matrix factorization

Jennifer Hsia, Peter J. Ramadge

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We experimentally examine how gradient descent navigates the landscape of matrix factorization to obtain a global minimum. First, we review the critical points of matrix factorization and introduce a balanced factorization. By focusing on the balanced critical point at the origin and a subspace of unbalanced critical points, we study the effect of balance on gradient descent, including an initially unbalanced factorization and adding a balance-regularizer to the objective in the MF problem. Simulations demonstrate that maintaining a balanced factorization enables faster escape from saddle points and overall faster convergence to a global minimum.

Original languageEnglish (US)
Title of host publication2021 55th Annual Conference on Information Sciences and Systems, CISS 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665412681
DOIs
StatePublished - Mar 24 2021
Externally publishedYes
Event55th Annual Conference on Information Sciences and Systems, CISS 2021 - Baltimore, United States
Duration: Mar 24 2021Mar 26 2021

Publication series

Name2021 55th Annual Conference on Information Sciences and Systems, CISS 2021

Conference

Conference55th Annual Conference on Information Sciences and Systems, CISS 2021
Country/TerritoryUnited States
CityBaltimore
Period3/24/213/26/21

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Information Systems and Management

Keywords

  • Balance
  • Gradient descent
  • Matrix factorization
  • Non-convex optimization
  • Saddle points

Fingerprint

Dive into the research topics of 'An experimental study of balance in matrix factorization'. Together they form a unique fingerprint.

Cite this