Description
The goal of this tutorial is to provide an overview of recent advances in landscape analysis for optimisation. The subject matter will be relevant to delegates who are interested in applying landscape analysis for the first time, but also to those involved in landscape analysis research to obtain a broader view of recent developments in the field. Fitness landscapes were first introduced to aid in the understanding of genetic evolution, but techniques were later developed for analysing fitness landscapes in the context of evolutionary computation. In the last decade, the field has experienced a large upswing in research, evident in the increased number of published papers on the topic as well as the appearance of tutorials, workshops and special sessions at all the major evolutionary computation conferences.
One of the changes that has emerged over the last decade is that the notion of fitness landscapes has been extended to include other views such as exploratory landscapes, landscape models (such as local optima networks), violation landscapes, error landscapes and loss landscapes. This tutorial will provide an overview of these different views on search spaces and how they relate. A number of new techniques for analysing landscapes have been developed and these will also be covered. In addition, an overview of recent applications of landscape analysis will be provided for understanding complex problems and algorithm behaviour, predicting algorithm performance and for automated algorithm configuration and selection. Case studies of the use of landscape analysis in both discrete and continuous domains will be presented. Finally, the tutorial will highlight some opportunities for future research in landscape analysis.
Plan and outline
The tutorial will start with a broad overview of the recent developments in the field, followed by case studies that highlight the practical use of landscape analysis in both discrete and continuous domains. The tutorial will include visual demonstrations and animations from case studies.
Proposed outline of topics to be covered:
- Fundamental concepts of fitness landscapes and early landscape analysis approaches.
- Complementary views to fitness landscapes: landscape models (local optima networks and search trajectory networks), exploratory landscapes, violation landscapes, error landscapes and loss landscapes.
- Using landscape models for detecting funnels, visualising and characterising search spaces (local optima networks) and understanding algorithm behaviour (search trajectory networks).
- Case study from the discrete domain, such as local optima networks applied to feature selection for classification.
- Case study from the continuous domain, such as landscape-aware algorithm selection for constraint-handling.
- Opportunities for future research in landscape analysis.