Levy walk evolution for global optimization
Date
2008-07Source Title
GECCO'08: Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation 2008
Publisher
ACM
Pages
537 - 538
Language
English
Type
Conference PaperItem Usage Stats
250
views
views
270
downloads
downloads
Abstract
A novel evolutionary global optimization approach based on adaptive covariance estimation is proposed. The proposed method samples from a multivariate Levy Skew Alpha-Stable distribution with the estimated covariance matrix to realize a random walk and so to generate new solution candidates in the mutation step. The proposed method is compared to the popular Differential Evolution method, which is one of the best general evolutionary global optimizers available. Experimental results indicate that the proposed approach yields a general improvement in the required number of function evaluations to solve global optimization problems. Especially, as shown in experiments, the underlying heavy tailed alpha-stable distribution enables a considerably more effective global search in more complex problems. Track: Evolution Strategies.
Keywords
Alpha-stable distributionEvolutionary optimization
Global optimization
Heavy tailed distribution
Levy walk
Covariance matrix
Evolutionary algorithms
Function evaluation
Optimization
Alpha-stable distributions
Complex problems
Covariance estimations
Differential evolution methods
Evolution strategies
Evolutionary global optimizations
Global optimization problems
Global searches
New solutions
Optimizers
Random walks
Permalink
http://hdl.handle.net/11693/26760Published Version (Please cite this version)
https://doi.org/10.1145/1389095.1389200Collections
Related items
Showing items related by title, author, creator and subject.
-
Optimal signaling and detector design for power constrained on-off keying systems in Neyman-Pearson framework
Dulek, Berkan; Gezici, Sinan (IEEE, 2011)Optimal stochastic signaling and detector design are studied for power constrained on-off keying systems in the presence of additive multimodal channel noise under the Neyman-Pearson (NP) framework. The problem of jointly ... -
On the optimality of stochastic signaling under an average power constraint
Göken, Çağrı; Gezici, Sinan; Arıkan, Orhan (IEEE, 2010-09-10)In this paper, stochastic signaling is studied for scalar valued binary communications systems over additive noise channels in the presence of an average power constraint. For a given decision rule at the receiver, the ... -
Randomized and rank based differential evolution
Urfalıoğlu, Onay; Arıkan, Orhan (IEEE, 2009-12)Many real world problems which can be assigned to the machine learning domain are inverse problems. The available data is often noisy and may contain outliers, which requires the application of global optimization. ...