Evolving the structure of Evolution Strategies
- 13 February 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
Various variants of the well known Covariance Matrix Adaptation Evolution Strategy (CMA-ES) have been proposed recently, which improve the empirical performance of the original algorithm by structural modifications. However, in practice it is often unclear which variation is best suited to the specific optimization problem at hand. As one approach to tackle this issue, algorithmic mechanisms attached to CMA-ES variants are considered and extracted as functional modules, allowing for combinations of them. This leads to a configuration space over ES structures, which enables the exploration of algorithm structures and paves the way toward novel algorithm generation. Specifically, eleven modules are incorporated in this framework with two or three alternative configurations for each module, resulting in 4 608 algorithms. A self-adaptive Genetic Algorithm (GA) is used to efficiently evolve effective ES-structures for given classes of optimization problems, outperforming any classical CMA-ES variants from literature. The proposed approach is evaluated on noiseless functions from BBOB suite. Furthermore, such an observation is again confirmed on different function groups and dimensionality, indicating the feasibility of ES configuration on real-world problem classes.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Evolving black-box search algorithms employing genetic programming2013
- On the log-normal self-adaptation of the mutation rate in binary search spaces2011
- Mirrored Sampling and Sequential Selection for Evolution Strategies2010
- Algorithms (X, sigma, eta): Quasi-random Mutations for Evolution StrategiesLecture Notes in Computer Science, 2006
- MPI for PythonJournal of Parallel and Distributed Computing, 2005
- Evolving Evolutionary Algorithms Using Linear Genetic ProgrammingEvolutionary Computation, 2005
- On the Evolution of Evolutionary AlgorithmsLecture Notes in Computer Science, 2004
- Empirical analysis of different levels of meta-evolution2003
- Evolving Evolutionary Algorithms Using Multi Expression Programming2003
- Meta-Evolution in Graph GP1999