Skip to Main content Skip to Navigation
Conference papers

Non-linearly increasing resampling in racing algorithms

Verena Heidrich-Meisner 1 Christian Igel 2 
1 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
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.
Document type :
Conference papers
Complete list of metadata

Cited literature [8 references]  Display  Hide  Download
Contributor : Verena Heidrich-Meisner Connect in order to contact the contributor
Submitted on : Monday, October 17, 2011 - 11:59:10 AM
Last modification on : Sunday, June 26, 2022 - 11:54:38 AM
Long-term archiving on: : Thursday, November 15, 2012 - 9:50:09 AM


Files produced by the author(s)


  • HAL Id : inria-00633006, version 1



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⟩



Record views


Files downloads