Competing with Markov prediction strategies

Research output: Working paper

131 Downloads (Pure)

Abstract

Assuming that the loss function is convex in the prediction, we construct a prediction strategy universal for the class of Markov prediction strategies, not necessarily continuous. Allowing randomization, we remove the requirement of convexity.
Original languageEnglish
Number of pages11
Publication statusPublished - 28 Jul 2006

Keywords

  • machine learning
  • prediction with expert advice

Cite this