Conference Papers Year : 2011

Non-linearly increasing resampling in racing algorithms

Verena Heidrich-Meisner
  • Function : Author
  • PersonId : 912343
Christian Igel
  • Function : Author
  • PersonId : 912344

Abstract

Racing algorithms are iterative methods for identifying the best among several options with high probability. The quality of each option is a random variable. It is estimated by its empirical mean and concentration bounds obtained from repeated sampling. In each iteration of a standard racing algorithm each promising option is reevaluated once before being statistically compared with its competitors. We argue that Hoeffding and empirical Bernstein races benefit from generalizing the functional dependence of the racing iteration and the number of samples per option and illustrate this on an artificial benchmark problem.
Fichier principal
Vignette du fichier
esann2011.pdf (134.19 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

inria-00633006 , version 1 (17-10-2011)

Identifiers

  • HAL Id : inria-00633006 , version 1

Cite

Verena Heidrich-Meisner, Christian Igel. Non-linearly increasing resampling in racing algorithms. European Symposium on Artificial Neural Networks, Apr 2011, Bruges, Belgium. pp.465-470. ⟨inria-00633006⟩
216 View
138 Download

Share

More