Adaptive Online Prediction by Following the Perturbed Leader

Simple item page
dc.creatorHutter, Marcus
dc.creatorPoland, Jan
dc.date2005-04-16
dc.date.accessioned2026-07-07T03:22:54Z
dc.date.available2026-07-07T03:22:54Z
dc.descriptionWhen applying aggregating strategies to Prediction with Expert Advice, the learning rate must be adaptively tuned. The natural choice of sqrt(complexity/current loss) renders the analysis of Weighted Majority derivatives quite complicated. In particular, for arbitrary weights there have been no results proven so far. The analysis of the alternative "Follow the Perturbed Leader" (FPL) algorithm from Kalai & Vempala (2003) (based on Hannan's algorithm) is easier. We derive loss bounds for adaptive learning rate and both finite expert classes with uniform weights and countable expert classes with arbitrary weights. For the former setup, our loss bounds match the best known results so far, while for the latter our results are new.
dc.description25 pages
dc.identifierhttps://arxiv.org/abs/cs/0504078
dc.identifierhttp://arxiv.org/abs/cs/0504078
dc.identifierJournal of Machine Learning Research 6 (2005) 639--660
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/32735
dc.subjectArtificial Intelligence
dc.subjectMachine Learning
dc.subjectI.2.6; G.3
dc.titleAdaptive Online Prediction by Following the Perturbed Leader
dc.typetext

Files

Collections

arXiv