Optimal robust expensive optimization is tractable - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2009

Optimal robust expensive optimization is tractable

Abstract

Following a number of recent papers investigating the possibility of optimal comparison-based optimization algorithms for a given distribution of probability on fitness functions, we (i) discuss the comparison-based constraints (ii) choose a setting in which theoretical tight bounds are known (iii) develop a careful implementation using billiard algorithms, Upper Confidence trees and (iv) experimentally test the tractability of the approach. The results, on still very simple cases, show that the approach, yet still preliminary, could be tested successfully until dimension 10 and horizon 50 iterations within a few hours on a standard computer, with convergence rate far better than the best algorithms.
Fichier principal
Vignette du fichier
balopt.pdf (177.41 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00374910 , version 1 (10-04-2009)

Identifiers

  • HAL Id : inria-00374910 , version 1

Cite

Philippe Rolet, Michèle Sebag, Olivier Teytaud. Optimal robust expensive optimization is tractable. Gecco 2009, ACM, 2009, Montréal, Canada. 8 p. ⟨inria-00374910⟩
277 View
318 Download

Share

Gmail Facebook X LinkedIn More