Defensive forecasting
Machine Learning
2007-05-23 v1 Artificial Intelligence
Abstract
We consider how to make probability forecasts of binary labels. Our main mathematical result is that for any continuous gambling strategy used for detecting disagreement between the forecasts and the actual labels, there exists a forecasting strategy whose forecasts are ideal as far as this gambling strategy is concerned. A forecasting strategy obtained in this way from a gambling strategy demonstrating a strong law of large numbers is simplified and studied empirically.
Cite
@article{arxiv.cs/0505083,
title = {Defensive forecasting},
author = {Vladimir Vovk and Akimichi Takemura and Glenn Shafer},
journal= {arXiv preprint arXiv:cs/0505083},
year = {2007}
}
Comments
15 pages, 2 figures, to appear in the AIStats'2005 electronic proceedings