ML Anthology

Defensive Forecasting

Vladimir Vovk, Akimichi Takemura, Glenn Shafer
AISTATS 2005 pp. 365-372
doi:10.48550/arxiv.cs/0505083 /aistats/2005/vovk2005aistats-defensive/

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.

PDF AISTATS Semantic Scholar

Cite

Text

Vovk et al. "Defensive Forecasting." Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics, 2005. doi:10.48550/arxiv.cs/0505083

Markdown

[Vovk et al. "Defensive Forecasting." Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics, 2005.](https://mlanthology.org/aistats/2005/vovk2005aistats-defensive/) doi:10.48550/arxiv.cs/0505083

BibTeX

@inproceedings{vovk2005aistats-defensive,
  title     = {{Defensive Forecasting}},
  author    = {Vovk, Vladimir and Takemura, Akimichi and Shafer, Glenn},
  booktitle = {Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics},
  year      = {2005},
  pages     = {365-372},
  doi       = {10.48550/arxiv.cs/0505083},
  volume    = {R5},
  url       = {https://mlanthology.org/aistats/2005/vovk2005aistats-defensive/}
}