Extrema Graphs: Fitness Landscape Analysis to the Extreme!

Extrema Graphs: Fitness Landscape Analysis to the Extreme!
复制标题

极值图:健身景观分析到极致!

DOI:
10.1145/3583133.3596343
复制
发表时间:
2023
期刊:
--
影响因子:
--
通讯作者:
Sadler S
Sadler S
中科院分区:
--
文献类型:
--
作者:
Sadler S

文献摘要

参考文献

相似文献

适应度景观分析通常依赖于视觉工具来提供对搜索空间的洞察,从而允许在优化之前进行推理。目前,可视化的主要方法是局部最优网络,其中潜在全局最优值周围的局部结构使用网络进行可视化,其中节点作为局部最小值,边缘作为通过优化器在这些最小值之间的过渡。在本文中,我们提出了一种基于极值图的方法,最初用于体积可视化中的等值面提取,其中通过降维技术(在我们的原型中的多维缩放)捕获嵌入在两个维度中的最大值和最小值之间的过渡。这些图使进化计算从业者能够通过结合描述极值之间的空间关系的全局信息来理解整个搜索空间。我们展示了一些连续的基准问题的方法,从文献中,并强调,由此产生的可视化,使观察已知的问题功能,从而得出结论,极值图是一个合适的工具,用于提取全球信息的问题景观。
Fitness landscape analysis often relies on visual tools to provide insight to a search space, allowing for reasoning before optimisation. Currently, the dominant approach for visualisation is the local optima network, where the local structure around a potential global optimum is visualised using a network with the nodes as local minima and the edges as transitions between those minima through an optimiser. In this paper, we present an approach based on extrema graphs, originally used for isosurface extraction in volume visualisation, where transitions are captured between both maxima and minima embedded in two dimensions through dimensionality reduction techniques (multidimensional scaling in our prototype). These diagrams enable evolutionary computation practitioners to understand the entire search space by incorporating global information describing the spatial relationships between extrema. We demonstrate the approach on a number of continuous benchmark problems from the literature and highlight that the resulting visualisations enable the observation of known problem features, leading to the conclusion that extrema graphs are a suitable tool for extracting global information about problem landscapes.
连续健身景观的局部最优网络
DOI: 10.1145/3319619.3326852
发表时间: 2019
期刊: --
影响因子: --
作者:
Adair J
通讯作者: Adair J
DOI: 10.1145/1389095.1389204
发表时间: 2008-07
期刊: --
影响因子: --
作者:
G. Ochoa;M. Tomassini;S. Vérel;Christian Darabos
通讯作者: G. Ochoa;M. Tomassini;S. Vérel;Christian Darabos
使用局部最优网络可视化多目标问题的情况
DOI: --
发表时间: 2019
期刊: Annual Conference on Genetic and Evolutionary Computation
影响因子: --
作者:
J. Fieldsend;Khulood AlYahya
通讯作者: Khulood AlYahya
DOI: --
发表时间: 2020
期刊: Parallel Problem Solving from Nature
影响因子: --
作者:
Mathew J. Walter;D. Walker;M. J. Craven
通讯作者: M. J. Craven
可视化搜索景观的全局结构:遗传改良作为案例研究
DOI: --
发表时间: 2018
影响因子: 2.6
作者:
Nadarajen Veerapen;G. Ochoa
通讯作者: G. Ochoa