Prediction with expert advice for the Brier game

Vladimir Vovk, Fedor Zhdanov

Research output: Working paper

156 Downloads (Pure)

Abstract

We show that the Brier game of prediction is mixable and find the optimal learning rate and substitution function for it. The resulting prediction algorithm is applied to predict results of football and tennis matches. The theoretical performance guarantee turns out to be rather tight on these datasets, especially in the case of the more extensive tennis data.
Original languageEnglish
Publication statusPublished - 2 Oct 2007

Keywords

  • cs.LG

Cite this