Empirical Inference
Technical Report
2003
A Note on Parameter Tuning for On-Line Shifting Algorithms
PDF PostScript
Empirical Inference
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.
| Author(s): | Bousquet, O. |
| Links: | |
| Year: | 2003 |
| Day: | 0 |
| BibTeX Type: | Technical Report (techreport) |
| Electronic Archiving: | grant_archive |
| Institution: | Max Planck Institute for Biological Cybernetics, Tübingen, Germany |
| Organization: | Max-Planck-Gesellschaft |
| School: | Biologische Kybernetik |
BibTeX
@techreport{2294,
title = {A Note on Parameter Tuning for On-Line Shifting Algorithms},
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.},
organization = {Max-Planck-Gesellschaft},
institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany},
school = {Biologische Kybernetik},
year = {2003},
author = {Bousquet, O.}
}