Analysis of runtime of optimization algorithms for noisy functions over discrete codomains

We consider in this work the application of optimization algorithms to problems over discrete codomains corrupted by additive unbiased noise. We propose a modification of the algorithms by repeating the fitness evaluation of the noisy function sufficiently so that, with a fix probability, the functi...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Theoretical computer science Ročník 605; s. 42 - 50
Hlavní autori: Akimoto, Youhei, Astete-Morales, Sandra, Teytaud, Olivier
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 09.11.2015
Elsevier
Predmet:
ISSN:0304-3975, 1879-2294
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:We consider in this work the application of optimization algorithms to problems over discrete codomains corrupted by additive unbiased noise. We propose a modification of the algorithms by repeating the fitness evaluation of the noisy function sufficiently so that, with a fix probability, the function evaluation on the noisy case is identical to the true value. If the runtime of the algorithms on the noise-free case is known, the number of resampling is chosen accordingly. If not, the number of resampling is chosen regarding to the number of fitness evaluations, in an anytime manner. We conclude that if the additive noise is Gaussian, then the runtime on the noisy case, for an adapted algorithm using resamplings, is similar to the runtime on the noise-free case: we incur only an extra logarithmic factor. If the noise is non-Gaussian but with finite variance, then the total runtime of the noisy case is quadratic in function of the runtime on the noise-free case.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0304-3975
1879-2294
DOI:10.1016/j.tcs.2015.04.008