Supermartingales in Prediction with Expert Advice

Alexey Chernov, Yuri Kalnishkan, Fedor Zhdanov, Vladimir Vovk

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBN

Abstract

This paper compares two methods of prediction with expert advice, the Aggregating Algorithm and the Defensive Forecasting, in two different settings. The first setting is traditional, with a countable number of experts and a finite number of outcomes. Surprisingly, these two methods of fundamentally different origin lead to identical procedures. In the second setting the experts can give advice conditional on the learner’s future decision. Both methods can be used in the new setting and give the same performance guarantees as in the traditional setting. However, whereas defensive forecasting can be applied directly, the AA requires substantial modifications.
Original languageEnglish
Title of host publication19th International Conference, ALT 2008
Place of PublicationBerlin
PublisherSpringer
Pages199-213
Number of pages15
Volume5254
DOIs
Publication statusPublished - 31 Dec 2008
Event19th International Conference, ALT 2008 - Budapest, Hungary, October 13-16, 2008
Duration: 31 Dec 2008 → …

Conference

Conference19th International Conference, ALT 2008
Period31/12/08 → …

    Fingerprint

Bibliographical note

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-540-87987-9_19

Cite this

Chernov, A., Kalnishkan, Y., Zhdanov, F., & Vovk, V. (2008). Supermartingales in Prediction with Expert Advice. In 19th International Conference, ALT 2008 (Vol. 5254, pp. 199-213). Berlin: Springer. https://doi.org/10.1007/978-3-540-87987-9_19