Defensive forecasting for optimal prediction with expert advice

Research output: Working paper

144 Downloads (Pure)

Abstract

The method of defensive forecasting is applied to the problem of prediction with expert advice for binary outcomes. It turns out that defensive forecasting is not only competitive with the Aggregating Algorithm but also handles the case of "second-guessing" experts, whose advice depends on the learner's prediction; this paper assumes that the dependence on the learner's prediction is continuous.
Original languageEnglish
Publication statusPublished - 10 Aug 2007

Keywords

  • cs.LG

Cite this