English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Report

A Note on Parameter Tuning for On-Line Shifting Algorithms

MPS-Authors
/persons/resource/persons83824

Bousquet,  O
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (public)

pdf2294.pdf
(Publisher version), 66KB

Supplementary Material (public)
There is no public supplementary material available
Citation

Bousquet, O.(2003). A Note on Parameter Tuning for On-Line Shifting Algorithms. Tübingen, Germany: Max Planck Institute for Biological Cybernetics.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-DDF2-F
Abstract
In this short note, building on ideas of M. Herbster [2] we propose a method for automatically tuning the parameter of the FIXED-SHARE algorithm proposed by Herbster and Warmuth [3] in the context of on-line learning with shifting experts. We show that this can be done with a memory requirement of O(nT) and that the additional loss incurred by the tuning is the same as the loss incurred for estimating the parameter of a Bernoulli random variable.