On the adaptation of the noise level for stochastic optimization

Olivier Teytaud 1 Anne Auger 1
1 TANC - Algorithmic number theory for cryptology
LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau], Inria Saclay - Ile de France
Abstract : This paper deals with the optimization of noisy fitness functions, where the noise level can be reduced by increasing the computational effort. We theoretically investigate the question of the control of the noise level. We analyse two different schemes for an adaptive control and prove sufficient conditions ensuring the existence of an homogeneous Markov chain, which is the first step to prove linear convergence when dealing with non-noisy fitness functions. We experimentally validate the relevance of the homogeneity criterion. Large-scale experiments conclude to the efficiency in a difficult framework.
Document type :
Conference papers
Complete list of metadatas

Cited literature [27 references]  Display  Hide  Download

https://hal.inria.fr/inria-00173224
Contributor : Olivier Teytaud <>
Submitted on : Wednesday, September 19, 2007 - 2:14:19 PM
Last modification on : Wednesday, March 27, 2019 - 4:41:29 PM
Long-term archiving on : Friday, April 9, 2010 - 2:29:10 AM

File

markovnoise.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00173224, version 1

Collections

Citation

Olivier Teytaud, Anne Auger. On the adaptation of the noise level for stochastic optimization. IEEE Congress on Evolutionary Computation, 2007, Singapour, Singapore. ⟨inria-00173224⟩

Share

Metrics

Record views

306

Files downloads

125