Follow the leader if you can, hedge if you must

de Rooij, Steven, van Erven, Tim, Grünwald, Peter D., & Koolen, Wouter M. (2014) Follow the leader if you can, hedge if you must. Journal of Machine Learning Research, 15, pp. 1281-1316.

View at publisher (open access)


Follow-the-Leader (FTL) is an intuitive sequential prediction strategy that guarantees constant regret in the stochastic setting, but has poor performance for worst-case data. Other hedging strategies have better worst-case guarantees but may perform much worse than FTL if the data are not maximally adversarial. We introduce the FlipFlop algorithm, which is the first method that provably combines the best of both worlds. As a stepping stone for our analysis, we develop AdaHedge, which is a new way of dynamically tuning the learning rate in Hedge without using the doubling trick. AdaHedge refines a method by Cesa-Bianchi, Mansour, and Stoltz (2007), yielding improved worst-case guarantees. By interleaving AdaHedge and FTL, FlipFlop achieves regret within a constant factor of the FTL regret, without sacrificing AdaHedge’s worst-case guarantees. AdaHedge and FlipFlop do not need to know the range of the losses in advance; moreover, unlike earlier methods, both have the intuitive property that the issued weights are invariant under rescaling and translation of the losses. The losses are also allowed to be negative, in which case they may be interpreted as gains.

Impact and interest:

11 citations in Scopus
Search Google Scholar™
2 citations in Web of Science®

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

ID Code: 73149
Item Type: Journal Article
Refereed: Yes
Additional URLs:
Keywords: Hedge, learning rate, mixability, online learning, prediction with expert advice
ISSN: 1533-7928
Divisions: Current > QUT Faculties and Divisions > Science & Engineering Faculty
Past > Schools > Mathematical Sciences
Copyright Owner: Copyright 2014 Steven de Rooij, Tim van Erven, Peter D. Grünwald and Wouter M. Koolen
Deposited On: 30 Jun 2014 22:53
Last Modified: 26 May 2015 22:05

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page