Online submodular minimization

  • Authors:
  • Elad Hazan;Satyen Kale

  • Affiliations:
  • Technion - Israel Inst. of Tech., Technion City, Haifa, Israel;IBM T.J. Watson Research Center, Yorktown Heights, NY

  • Venue:
  • The Journal of Machine Learning Research
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

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.