Simon Wessing
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Simon Wessing has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Mike Preuss
Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands
5 shared publications Günter Rudolph
Technische Universität Dortmund
3 shared publications- Nicola Beume
TU Dortmund
2 shared publications Andreas Thom
Chair of Algorithm Engineering, Computational Intelligence Group, Dept. of Computer Science, Technische Universität Dortmund, Dortmund, Germany
1 shared publicationB Naujoks
Faculty of Computer Science and Engineering Science, Cologne University of Applied Sciences, Gummersbach, Germany
1 shared publication- Boris Naujoks
Chair of Algorithm Engineering, Computational Intelligence Group, Dept. of Computer Science, Technische Universität Dortmund, Dortmund, Germany
1 shared publication
Latest Publications
- 1 March 2019
- Published by MIT Press in Evolutionary Computation
- Vol. 27 (1) , 129-145
Latin Hypercube Designs with Branching and Nested Factors for Initialization of Automatic Algorithm Configuration
The configuration of algorithms is a laborious and difficult process. Thus, it is advisable to automate this task by using appropriate automatic configuration methods. The [ ] method is among the most widely used in the literature. By default, [ ] initializes its search process via uniform sampling of algorithm configurations. Although better initialization methods exist in the literature, the mixed-variable (numerical and categorical) nature of typical parameter spaces and the presence of conditional parameters make most of the methods not applicable in practice. Here, we present an improved initialization method that overcomes these limitations by employing concepts from the design and analysis of computer experiments with branching and nested factors. Our results show that this initialization method is not only better, in some scenarios, than the uniform sampling used by the current version of [ ], but also better than other initialization methods present in other automatic configuration methods.
- 1 March 2019
- Published by MIT Press in Evolutionary Computation
- Vol. 27 (1) , 129-145
Latin Hypercube Designs with Branching and Nested Factors for Initialization of Automatic Algorithm Configuration
The configuration of algorithms is a laborious and difficult process. Thus, it is advisable to automate this task by using appropriate automatic configuration methods. The [ ] method is among the most widely used in the literature. By default, [ ] initializes its search process via uniform sampling of algorithm configurations. Although better initialization methods exist in the literature, the mixed-variable (numerical and categorical) nature of typical parameter spaces and the presence of conditional parameters make most of the methods not applicable in practice. Here, we present an improved initialization method that overcomes these limitations by employing concepts from the design and analysis of computer experiments with branching and nested factors. Our results show that this initialization method is not only better, in some scenarios, than the uniform sampling used by the current version of [ ], but also better than other initialization methods present in other automatic configuration methods.
- 25 June 2018
- Published by Springer Nature in Optimization Letters
- Vol. 13 (4) , 847-856
Proper initialization is crucial for the Nelder–Mead simplex search
- 25 June 2018
- Published by Springer Nature in Optimization Letters
- Vol. 13 (4) , 847-856
Proper initialization is crucial for the Nelder–Mead simplex search
- Open Access
Experimental Analysis of a Generalized Stratified Sampling Algorithm for Hypercubes
Stratified sampling is a fast and simple method to generate point sets with uniform distribution in hypercubes. However, for the most common paraxial stratfication it has the prominent drawback that the number of sampled points in n dimensions has to be an n-th power of an integer number. This exponential growth makes its application unattractive or even infeasible in high dimensions. We present a stratification procedure that eliminates this problem by a recursive binary partitioning of the hypercube. The algorithm runs in linear time and tries to minimize the hyperboxes' deviation from the cubic shape. We analyze the properties of the algorithm using discrepancy and covering radius, and directly in practical applications, comparing it to quasirandom and other sampling methods. We also discuss a potential combination with Latin hypercube sampling, which positively affects discrepancy.
Open AccessExperimental Analysis of a Generalized Stratified Sampling Algorithm for Hypercubes
Stratified sampling is a fast and simple method to generate point sets with uniform distribution in hypercubes. However, for the most common paraxial stratfication it has the prominent drawback that the number of sampled points in n dimensions has to be an n-th power of an integer number. This exponential growth makes its application unattractive or even infeasible in high dimensions. We present a stratification procedure that eliminates this problem by a recursive binary partitioning of the hypercube. The algorithm runs in linear time and tries to minimize the hyperboxes' deviation from the cubic shape. We analyze the properties of the algorithm using discrepancy and covering radius, and directly in practical applications, comparing it to quasirandom and other sampling methods. We also discuss a potential combination with Latin hypercube sampling, which positively affects discrepancy.
- Open Access
The True Destination of EGO is Multi-local Optimization
Efficient global optimization is a popular algorithm for the optimization of expensive multimodal black-box functions. One important reason for its popularity is its theoretical foundation of global convergence. However, as the budgets in expensive optimization are very small, the asymptotic properties only play a minor role and the algorithm sometimes comes off badly in experimental comparisons. Many alternative variants have therefore been proposed over the years. In this work, we show experimentally that the algorithm instead has its strength in a setting where multiple optima are to be identified.
Open AccessThe True Destination of EGO is Multi-local Optimization
Efficient global optimization is a popular algorithm for the optimization of expensive multimodal black-box functions. One important reason for its popularity is its theoretical foundation of global convergence. However, as the budgets in expensive optimization are very small, the asymptotic properties only play a minor role and the algorithm sometimes comes off badly in experimental comparisons. Many alternative variants have therefore been proposed over the years. In this work, we show experimentally that the algorithm instead has its strength in a setting where multiple optima are to be identified.
- 19 February 2017
- Published by Springer Nature
- p. 670-684
Toward Step-Size Adaptation in Evolutionary Multiobjective Optimization
- 19 February 2017
- Published by Springer Nature
- p. 670-684
Toward Step-Size Adaptation in Evolutionary Multiobjective Optimization
- 5 November 2016
- Published by Springer Nature
- p. 53-70
Assessing Basin Identification Methods for Locating Multiple Optima
- 5 November 2016
- Published by Springer Nature
- p. 53-70
Assessing Basin Identification Methods for Locating Multiple Optima
- 31 August 2016
- Published by Springer Nature
- p. 558-567
Comparing Asynchronous and Synchronous Parallelization of the SMS-EMOA
- 31 August 2016
- Published by Springer Nature
- p. 558-567
Comparing Asynchronous and Synchronous Parallelization of the SMS-EMOA
- Open Access
Towards a Systematic Development Process of Optimization Methods
The ultimate goal of all optimization methods is to solve real-world problems. For a successful project execution, knowledge about optimization and the application has to be pooled. As it is too inefficient to highly train one person in both fields, a team of experts is usually put together. Unfortunately, communication errors must be expected when several people collaborate. In this work, we deal with the avoidance and the repair of these communication errors. The tools proposed in this regard are, among others, the algorithm engineering cycle, checklists for structuring communication, and knowledge databases. The discussion is enriched with examples from continuous optimization, but most tools have a much wider applicability, even beyond optimization.
Open AccessTowards a Systematic Development Process of Optimization Methods
The ultimate goal of all optimization methods is to solve real-world problems. For a successful project execution, knowledge about optimization and the application has to be pooled. As it is too inefficient to highly train one person in both fields, a team of experts is usually put together. Unfortunately, communication errors must be expected when several people collaborate. In this work, we deal with the avoidance and the repair of these communication errors. The tools proposed in this regard are, among others, the algorithm engineering cycle, checklists for structuring communication, and knowledge databases. The discussion is enriched with examples from continuous optimization, but most tools have a much wider applicability, even beyond optimization.
- 5 September 2015
- Published by Springer Nature in Computational Optimization and Applications
- Vol. 63 (3) , 875-902
On multiobjective selection for multimodal optimization
- 5 September 2015
- Published by Springer Nature in Computational Optimization and Applications
- Vol. 63 (3) , 875-902
On multiobjective selection for multimodal optimization
- 1 January 2015
- Published by Springer Nature
- p. 1159-1171
Solving Phase Equilibrium Problems by Means of Avoidance-Based Multiobjectivization
- 1 January 2015
- Published by Springer Nature
- p. 1159-1171
Solving Phase Equilibrium Problems by Means of Avoidance-Based Multiobjectivization