Asymptotic uniqueness in long-term prediction

Vladimir Vovk
Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications, PMLR 230:90-104, 2024.

Abstract

This paper establishes the asymptotic uniqueness of long-term probability forecasts in the following form. Consider two forecasters who repeatedly issue probability forecasts for the infinite future. The main result of the paper says that either at least one of the two forecasters will be discredited or their forecasts will converge in total variation. This can be regarded as a game-theoretic version of the classical Blackwell–Dubins result getting rid of some of its limitations. This result is further strengthened along the lines of Richard Jeffrey’s radical probabilism.

Cite this Paper

BibTeX
@InProceedings{pmlr-v230-vovk24a, title = {Asymptotic uniqueness in long-term prediction}, author = {Vovk, Vladimir}, booktitle = {Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications}, pages = {90--104}, year = {2024}, editor = {Vantini, Simone and Fontana, Matteo and Solari, Aldo and Boström, Henrik and Carlsson, Lars}, volume = {230}, series = {Proceedings of Machine Learning Research}, month = {09--11 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v230/main/assets/vovk24a/vovk24a.pdf}, url = {https://proceedings.mlr.press/v230/vovk24a.html}, abstract = {This paper establishes the asymptotic uniqueness of long-term probability forecasts in the following form. Consider two forecasters who repeatedly issue probability forecasts for the infinite future. The main result of the paper says that either at least one of the two forecasters will be discredited or their forecasts will converge in total variation. This can be regarded as a game-theoretic version of the classical Blackwell–Dubins result getting rid of some of its limitations. This result is further strengthened along the lines of Richard Jeffrey’s radical probabilism.} }
Endnote
%0 Conference Paper %T Asymptotic uniqueness in long-term prediction %A Vladimir Vovk %B Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications %C Proceedings of Machine Learning Research %D 2024 %E Simone Vantini %E Matteo Fontana %E Aldo Solari %E Henrik Boström %E Lars Carlsson %F pmlr-v230-vovk24a %I PMLR %P 90--104 %U https://proceedings.mlr.press/v230/vovk24a.html %V 230 %X This paper establishes the asymptotic uniqueness of long-term probability forecasts in the following form. Consider two forecasters who repeatedly issue probability forecasts for the infinite future. The main result of the paper says that either at least one of the two forecasters will be discredited or their forecasts will converge in total variation. This can be regarded as a game-theoretic version of the classical Blackwell–Dubins result getting rid of some of its limitations. This result is further strengthened along the lines of Richard Jeffrey’s radical probabilism.
APA
Vovk, V.. (2024). Asymptotic uniqueness in long-term prediction. Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications, in Proceedings of Machine Learning Research 230:90-104 Available from https://proceedings.mlr.press/v230/vovk24a.html.

Related Material