Return to search

Online Learning of Non-stationary Sequences

We consider an online learning scenario in which the learner can make predictions on the basis of a fixed set of experts. We derive upper and lower relative loss bounds for a class of universal learning algorithms involving a switching dynamics over the choice of the experts. On the basis of the performance bounds we provide the optimal a priori discretization of the switching-rate parameter that governs the switching dynamics. We demonstrate the algorithm in the context of wireless networks.

Identiferoai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/30584
Date17 November 2005
CreatorsMonteleoni, Claire, Jaakkola, Tommi
Source SetsM.I.T. Theses and Dissertation
Languageen_US
Detected LanguageEnglish
Format8 p., 10189026 bytes, 760649 bytes, application/postscript, application/pdf
RelationMassachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory

Page generated in 0.0017 seconds