Online submodular minimization

Elad Hazan, Satyen Kale

Research output: Contribution to journalArticlepeer-review

20 Scopus citations

Abstract

We consider an online decision problem over a discrete space in which the loss function is submodular. We give algorithms which are computationally efficient and are Hannan-consistent in both the full information and partial feedback settings.

Original languageEnglish (US)
Pages (from-to)2903-2922
Number of pages20
JournalJournal of Machine Learning Research
Volume13
StatePublished - Oct 2012
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Statistics and Probability
  • Artificial Intelligence

Keywords

  • Online learning
  • Regret minimization
  • Submodular optimization

Fingerprint Dive into the research topics of 'Online submodular minimization'. Together they form a unique fingerprint.

Cite this