Skip navigation
Skip navigation

Adaptive online prediction by following the perturbed leader

Hutter, Marcus; Poland, Jan

Description

When applying aggregating strategies to Prediction with Expert Advice (PEA), the learning rate must be adaptively tuned. The natural choice of √ complexity/current loss renders the analysis of Weighted Majority (WM) 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 and Vempala (2003) based on Hannan’s algorithm is easier. We derive loss bounds...[Show more]

CollectionsANU Research Publications
Date published: 2005-04
Type: Journal article
URI: http://hdl.handle.net/1885/15049
Source: Journal of Machine Learning Research

Download

File Description SizeFormat Image
Hutter and Poland Adaptive Online Prediction 2005.pdf187.12 kBAdobe PDFThumbnail


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  12 November 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator