Adaptive Noisy Optimization - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2010

Adaptive Noisy Optimization


In this paper, adaptive noisy optimization on variants of the noisy sphere model is considered, i.e. optimization in which the same algorithm is able to adapt to several frameworks, including some for which no bound has never been derived. Incidentally, bounds derived by [16] for noise quickly decreasing to zero around the optimum are extended to the more general case of a positively lower-bounded noise thanks to a careful use of Bernstein bounds (using empirical estimates of the variance) instead of Chernoff-like variants
Fichier principal
Vignette du fichier
evostar2010.pdf (174.89 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00459017 , version 1 (09-03-2010)


  • HAL Id : inria-00459017 , version 1


Philippe Rolet, Olivier Teytaud. Adaptive Noisy Optimization. EvoStar 2010, Apr 2010, Istambul, Turkey. ⟨inria-00459017⟩
340 View
231 Download


Gmail Facebook Twitter LinkedIn More