Prediction with Advice of Unknown Number of Experts

Alexey Chernov, Vladimir Vovk
Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, PMLR R8:125-133, 2010.

Abstract

In the framework of prediction with expert advice, we consider a recently introduced kind of regret bounds: the bounds that depend on the effective instead of nominal number of experts. In contrast to the Normal- Hedge bound, which mainly depends on the effective number of experts but also weakly depends on the nominal one, we obtain a bound that does not contain the nominal number of experts at all. We use the defensive forecasting method and introduce an application of defensive forecasting to multivalued supermartingales.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR8-chernov10a, title = {Prediction with Advice of Unknown Number of Experts}, author = {Chernov, Alexey and Vovk, Vladimir}, booktitle = {Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence}, pages = {125--133}, year = {2010}, editor = {Grünwald, Peter and Spirtes, Peter}, volume = {R8}, series = {Proceedings of Machine Learning Research}, month = {08--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r8/main/assets/chernov10a/chernov10a.pdf}, url = {https://proceedings.mlr.press/r8/chernov10a.html}, abstract = {In the framework of prediction with expert advice, we consider a recently introduced kind of regret bounds: the bounds that depend on the effective instead of nominal number of experts. In contrast to the Normal- Hedge bound, which mainly depends on the effective number of experts but also weakly depends on the nominal one, we obtain a bound that does not contain the nominal number of experts at all. We use the defensive forecasting method and introduce an application of defensive forecasting to multivalued supermartingales.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Prediction with Advice of Unknown Number of Experts %A Alexey Chernov %A Vladimir Vovk %B Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2010 %E Peter Grünwald %E Peter Spirtes %F pmlr-vR8-chernov10a %I PMLR %P 125--133 %U https://proceedings.mlr.press/r8/chernov10a.html %V R8 %X In the framework of prediction with expert advice, we consider a recently introduced kind of regret bounds: the bounds that depend on the effective instead of nominal number of experts. In contrast to the Normal- Hedge bound, which mainly depends on the effective number of experts but also weakly depends on the nominal one, we obtain a bound that does not contain the nominal number of experts at all. We use the defensive forecasting method and introduce an application of defensive forecasting to multivalued supermartingales. %Z Reissued by PMLR on 04 October 2026.
APA
Chernov, A. & Vovk, V.. (2010). Prediction with Advice of Unknown Number of Experts. Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R8:125-133 Available from https://proceedings.mlr.press/r8/chernov10a.html. Reissued by PMLR on 04 October 2026.

Related Material