Tuning & simplifying heuristical optimization
Tuning & simplifying heuristical optimization
This thesis is about the tuning and simplification of black-box (direct-search, derivative-free) optimization methods, which by definition do not use gradient information to guide their search for an optimum but merely need a fitness (cost, error, objective) measure for each candidate solution to the optimization problem. Such optimization methods often have parameters that infuence their behaviour and efficacy. A Meta-Optimization technique is presented here for tuning the behavioural parameters of an optimization method by employing an additional layer of optimization. This is used in a number of experiments on two popular optimization methods, Differential Evolution and Particle Swarm Optimization, and unveils the true performance capabilities of an optimizer in different usage scenarios. It is found that state-of-the-art optimizer variants with their supposedly adaptive behavioural parameters do not have a general and consistent performance advantage but are outperformed in several cases by simplified optimizers, if only the behavioural parameters are tuned properly.
Pedersen, Magnus Erik Hvass
934a72ff-822d-4a29-bd13-991136738f18
January 2010
Pedersen, Magnus Erik Hvass
934a72ff-822d-4a29-bd13-991136738f18
Chipperfield, A.J.
524269cd-5f30-4356-92d4-891c14c09340
Pedersen, Magnus Erik Hvass
(2010)
Tuning & simplifying heuristical optimization.
University of Southampton, Shool of Engineering Science, Doctoral Thesis, 204pp.
Record type:
Thesis
(Doctoral)
Abstract
This thesis is about the tuning and simplification of black-box (direct-search, derivative-free) optimization methods, which by definition do not use gradient information to guide their search for an optimum but merely need a fitness (cost, error, objective) measure for each candidate solution to the optimization problem. Such optimization methods often have parameters that infuence their behaviour and efficacy. A Meta-Optimization technique is presented here for tuning the behavioural parameters of an optimization method by employing an additional layer of optimization. This is used in a number of experiments on two popular optimization methods, Differential Evolution and Particle Swarm Optimization, and unveils the true performance capabilities of an optimizer in different usage scenarios. It is found that state-of-the-art optimizer variants with their supposedly adaptive behavioural parameters do not have a general and consistent performance advantage but are outperformed in several cases by simplified optimizers, if only the behavioural parameters are tuned properly.
Text
MEH_Pedersen_PhD_Thesis_2010.pdf
- Other
More information
Published date: January 2010
Organisations:
University of Southampton, Engineering Science Unit
Identifiers
Local EPrints ID: 342792
URI: http://eprints.soton.ac.uk/id/eprint/342792
PURE UUID: ee480425-ad04-42b3-87e0-07a70223ca2b
Catalogue record
Date deposited: 16 Nov 2012 16:30
Last modified: 15 Mar 2024 03:15
Export record
Contributors
Author:
Magnus Erik Hvass Pedersen
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
