Defensive forecasting for linear protocols

Details Defensive forecasting for linear protocols Defensive forecasting for linear protocols

2005-06-02

arxiv.org/abs/cs/0506007v2

Computer Science

Learning

16 pages

Scientific paper

We consider a general class of forecasting protocols, called "linear protocols", and discuss several important special cases, including multi-class forecasting. Forecasting is formalized as a game between three players: Reality, whose role is to generate observations; Forecaster, whose goal is to predict the observations; and Skeptic, who tries to make money on any lack of agreement between Forecaster's predictions and the actual observations. Our main mathematical result is that for any continuous strategy for Skeptic in a linear protocol there exists a strategy for Forecaster that does not allow Skeptic's capital to grow. This result is a meta-theorem that allows one to transform any continuous law of probability in a linear protocol into a forecasting strategy whose predictions are guaranteed to satisfy this law. We apply this meta-theorem to a weak law of large numbers in Hilbert spaces to obtain a version of the K29 prediction algorithm for linear protocols and show that this version also satisfies the attractive properties of proper calibration and resolution under a suitable choice of its kernel parameter, with no assumptions about the way the data is generated.

Affiliated with

Also associated with

No associations

Rating

Defensive forecasting for linear protocols does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Defensive forecasting for linear protocols, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Defensive forecasting for linear protocols will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-434749