Skip to main content
Home > Research
Research > Tutorials

Selection, Exploration, and Exploitation

Abstract

The goal of exploration is to seek out new areas of the search space. The effect of selection is to concentrate search around the best-known areas of the search space. The power of selection can overwhelm exploration, allowing it to turn any exploratory method into a hill climber. The balancing of exploration and exploitation requires more than the consideration of what solutions are created -- it requires an analysis of the interplay between exploration and selection.

This tutorial reviews a broad range of selection methods used in metaheuristics. Novel tools to analyze the effects of selection on exploration in the continuous domain are introduced and demonstrated on Particle Swarm Optimization and Differential Evolution. The difference between convergence (no exploratory search solutions are created) and stall (all exploratory search solutions are rejected) is highlighted. Remedies and alternate methods of selection are presented, and the ramifications for the future design of metaheuristics are discussed.

Target Audience

This tutorial has both introductory and intermediate components. The survey of selection methods in metaheuristics will be useful to both new and established researchers. The deeper analysis of selection for continuous domains focuses on Particle Swarm Optimization and Differential Evolution, and experience with a Swarm Intelligence or Evolutionary Computation based method in continuous domain, multi-modal search spaces will be of benefit.

Presentation Slides

To be posted approximately one week before the tutorial.

Presenters

Stephen Chen Image

Stephen Chen is an Associate Professor in the School of Information Technology at York University in Toronto, Canada. His research focuses on analyzing the mechanisms for exploration and exploitation in techniques designed for multi-modal optimization problems. He is particularly interested in the development and analysis of non-metaphor-based heuristic search techniques. He has conducted extensive research on genetic algorithms and swarm-based optimization systems, and his 60+ peer-reviewed publications include 20+ that have been presented at previous CEC events.

James Montgomery Image

James Montgomery is a Senior Lecturer in the School of Technology, Environments and Design at the University of Tasmania in Hobart, Australia. His research focuses on search space analysis and the design of solution representations for complex, real-world problems. He has conducted extensive research on ant colony optimization and differential evolution, and his 50+ peer-reviewed publications include 10+ that have been presented at previous CEC events.